© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1451
    Prev
    Next
    INDEX
    Explanations

    conditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ChangeString
    1.10
    <unused1291>
    1.07
     सिंपली
    1.07
     国産
    1.06
     中国证券投资基金业协会
    1.06
    <unused1610>
    1.05
     Pusenk
    1.05
    <unused44>
    1.04
     গেরিলাদের
    1.03
    iyatiti
    1.03
    POSITIVE LOGITS
     bag
    0.99
     pack
    0.87
     kit
    0.85
     dr
    0.81
     পঞ্চ
    0.81
     bags
    0.79
     vil
    0.78
     within
    0.77
     from
    0.75
     worthy
    0.74
    Activations Density 0.000%

    No Known Activations