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. 8152
    Prev
    Next
    INDEX
    Explanations

    bachelor's degrees

    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
     peint
    1.08
     lumi
    0.96
    Auction
    0.96
    aj
    0.94
    ি
    0.93
     Stunden
    0.92
    t
    0.91
     heen
    0.91
    IR
    0.89
     conducir
    0.89
    POSITIVE LOGITS
     cử
    1.07
    Ꮹ
    1.07
    riam
    1.05
    ྂ
    1.05
     рода
    1.04
     avem
    1.03
     образование
    1.01
    。</
    1.00
     fiancée
    1.00
    堕
    1.00
    Activations Density 0.009%

    No Known Activations