© 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-262K
    7. 241452
    Prev
    Next
    INDEX
    Explanations

    self

    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_262k_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
    wer
    0.56
    abil
    0.56
    ORIG
    0.55
    сре
    0.55
    bol
    0.55
    abol
    0.55
    erapia
    0.55
    咨
    0.54
    that
    0.53
    emas
    0.52
    POSITIVE LOGITS
     Setter
    0.55
    NIOS
    0.55
    ".*:
    0.54
     delhi
    0.54
    ^{\#}\
    0.53
     quantifier
    0.53
    𝕋
    0.53
     dSample
    0.52
     thường
    0.51
     região
    0.51
    Activations Density 0.000%

    No Known Activations