Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1255
    Prev
    Next
    INDEX
    Explanations

    Belt, goddess, mortal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     dùng
    0.96
     toning
    0.95
     कोणत्याही
    0.94
    etchup
    0.94
    ależy
    0.93
    晾
    0.91
     macroeconomic
    0.91
     housewife
    0.90
     depreciation
    0.89
     તમને
    0.89
    POSITIVE LOGITS
    !
    1.26
    ⚔
    1.09
     erricht
    1.08
     undead
    1.07
    Terror
    1.07
    Weapon
    1.04
    ?
    1.03
     Outreach
    1.02
     selatan
    0.98
     ogrom
    0.97
    Activations Density 0.627%

    No Known Activations