© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    command preceded by word or token

    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_16k_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
    is
    0.89
    h
    0.87
    j
    0.82
    yb
    0.80
    sale
    0.77
    ד
    0.77
    g
    0.73
    hh
    0.73
    hg
    0.72
    hhhh
    0.71
    POSITIVE LOGITS
    Қ
    1.05
    ে
    1.02
    ε
    1.00
    いますが
    0.97
    Cadastro
    0.95
    ી
    0.95
    混凝土
    0.94
    நிலை
    0.93
     EnglishChoose
    0.93
    Muscle
    0.93
    Activations Density 0.004%

    No Known Activations