© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15304
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    აძ
    0.65
    ijiet
    0.57
    hill
    0.55
    athy
    0.55
    ште
    0.55
    azaki
    0.54
    zés
    0.53
    舰
    0.53
    넥
    0.53
    珽
    0.52
    POSITIVE LOGITS
    ively
    2.75
    ive
    2.22
    iveness
    2.11
    ivity
    2.06
    ives
    1.97
    ivism
    1.88
    ual
    1.86
    ually
    1.84
    IVE
    1.76
    ional
    1.73
    Activations Density 0.146%

    No Known Activations