© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    help others or self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    Di
    0.80
    CA
    0.80
    Vol
    0.78
    S
    0.77
    A
    0.75
    C
    0.74
    T
    0.74
    F
    0.72
    L
    0.71
    Lot
    0.71
    POSITIVE LOGITS
     personnes
    0.96
     financière
    0.94
     unterschied
    0.94
     nás
    0.90
     herkese
    0.90
     anderen
    0.89
    充実
    0.88
     us
    0.88
     manière
    0.88
     自分
    0.87
    Activations Density 0.805%

    No Known Activations