© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1720
    Prev
    Next
    INDEX
    Explanations

    option for

    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_65k_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
    _
    0.54
    )$.
    0.51
    com
    0.50
    $,
    0.46
    iol
    0.46
     পরিবর্ত
    0.46
    是
    0.46
    ），
    0.46
    <0x0D>
    0.45
    ít
    0.45
    POSITIVE LOGITS
     একখানি
    0.46
     géographique
    0.44
    образной
    0.44
     ಏಕೆಂದರೆ
    0.43
    嚶
    0.43
     पुरंदरे
    0.43
    obacterial
    0.43
     totalement
    0.43
     suppuration
    0.43
    র্ভাব
    0.43
    Activations Density 0.007%

    No Known Activations