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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14063
    Prev
    Next
    INDEX
    Explanations

    downsides, unlike, please

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sachen
    0.42
    .
    0.42
     convolutions
    0.42
     arbitrage
    0.41
     lexicon
    0.41
     deluge
    0.40
     caveats
    0.40
     grün
    0.40
     dialects
    0.40
     heresy
    0.40
    POSITIVE LOGITS
    <td>
    0.40
    家庭
    0.37
    रो
    0.36
    <div>
    0.36
    𝑃
    0.36
     కుటుంబ
    0.35
    abhuto
    0.34
    ራሉ
    0.34
    期待
    0.34
    家里
    0.33
    Activations Density 0.184%

    No Known Activations