© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 390
    Prev
    Next
    INDEX
    Explanations

    describes information

    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
     T
    1.22
     P
    1.08
     S
    1.02
     G
    1.02
     W
    1.02
     U
    0.96
     B
    0.94
    はこちら
    0.93
     C
    0.93
     didn
    0.92
    POSITIVE LOGITS
    as
    1.60
    id
    1.45
    ar
    1.36
    al
    1.35
    criar
    1.23
    y
    1.23
    ро
    1.22
    en
    1.19
    اٹ
    1.14
    es
    1.13
    Activations Density 0.041%

    No Known Activations