© 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. 14820
    Prev
    Next
    INDEX
    Explanations

    NH NV abbreviations

    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
     alone
    0.56
    തം
    0.51
    几十
    0.51
    덴
    0.49
    有效的
    0.49
     nazy
    0.49
    なった
    0.48
    ችን
    0.48
    alone
    0.47
     Ol
    0.47
    POSITIVE LOGITS
     NH
    1.02
     nh
    0.86
     Nh
    0.84
    NH
    0.73
    Nh
    0.68
    ibernate
    0.65
    Ữ
    0.63
    ordano
    0.62
     Ammonium
    0.60
    èdes
    0.60
    Activations Density 0.015%

    No Known Activations