© 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. 1739
    Prev
    Next
    INDEX
    Explanations

    tilt and angles

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

    The neuron consistently activates on occurrences of the word “tilt” (including compounds like “tilt-rotor,” “tilt-table,” and “tilt-test”).

    oai_token-act-pair · o4-miniTriggered 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
    瑧
    -2.56
     良品
    -2.55
     Surprisingly
    -2.55
    ⇰
    -2.50
     –
    -2.41
    na
    -2.27
     tyranny
    -2.27
    ٙ
    -2.23
    鋮
    -2.23
    黴
    -2.17
    POSITIVE LOGITS
    蠖
    3.48
    汌
    3.34
    </strong>
    3.09
    鞮
    2.86
    珵
    2.77
    哙
    2.72
    鹪
    2.53
    </h3>
    2.45
     the
    2.42
    齮
    2.41
    Activations Density 0.005%

    No Known Activations