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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35477
    Prev
    Next
    INDEX
    Explanations

    dividing into smaller parts

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the word “chunk” (e.g. in settings like CHUNK_SIZE).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     betekent
    -2.59
    栳
    -2.55
     seduta
    -2.34
    谖
    -2.33
     ajustar
    -2.33
    盌
    -2.28
     jesteś
    -2.22
    但
    -2.22
     They
    -2.20
     chiaramente
    -2.20
    POSITIVE LOGITS
    \
    2.53
    <bos>
    2.42
    \_
    2.38
    '
    2.17
     развития
    2.17
     «
    2.13
    好人
    2.13
    end
    2.02
     борьбе
    2.00
    铩
    2.00
    Activations Density 0.007%

    No Known Activations