Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44549
    Prev
    Next
    INDEX
    Explanations

    simple explanation

    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
    AN
    1.30
    an
    1.21
    in
    1.19
    AR
    1.11
    u
    1.10
    ar
    1.05
    ERS
    1.05
    er
    1.04
    ES
    1.04
    weird
    1.02
    POSITIVE LOGITS
     faiblement
    1.03
     scegli
    0.97
     choisissez
    0.93
     maiores
    0.90
     prenez
    0.89
     requis
    0.88
     <!
    0.87
    క్కువ
    0.86
     Helium
    0.85
     escrow
    0.85
    Activations Density 0.010%

    No Known Activations