© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69499
    Prev
    Next
    INDEX
    Explanations

    analysis of data

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “analysis” (in any case) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of analysis processes, especially in technical, scientific, or code-related contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "analysis" in technical and scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -4.22
    旆
    -2.70
     we
    -2.34
    嫑
    -2.33
    СКИ
    -2.33
    鲞
    -2.31
    ጺ
    -2.27
    鹛
    -2.16
    囖
    -2.14
     becauſe
    -2.11
    POSITIVE LOGITS
    it
    2.88
    in
    2.53
    曁
    2.41
    呖
    2.33
    .
    2.30
    )$
    2.28
     of
    2.28
    辔
    2.27
    蛧
    2.25
            
    2.23
    Activations Density 0.045%

    No Known Activations