© 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-262K
    7. 41196
    Prev
    Next
    INDEX
    Explanations

    desires to engage

    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
     ຈ
    0.50
     سنی
    0.48
    =.
    0.47
    /.
    0.46
     imedi
    0.46
     ५
    0.46
    ,..
    0.46
    ６
    0.45
    {.
    0.45
     १५
    0.45
    POSITIVE LOGITS
    ার
    0.48
    anoate
    0.45
     вули
    0.43
    лях
    0.43
    er
    0.42
    ниць
    0.42
    प्ताहिक
    0.42
     FAQ
    0.40
    iegen
    0.40
     Issuer
    0.39
    Activations Density 0.000%

    No Known Activations