© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11993
    Prev
    Next
    INDEX
    Explanations

    'm and 'd contractions

    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
     núcle
    1.14
    sadpoetry
    1.02
    ákat
    0.99
     الفر
    0.98
    permissionid
    0.96
    􀂃
    0.96
    頎
    0.96
     दमखम
    0.96
    իմ
    0.94
    jobSize
    0.93
    POSITIVE LOGITS
    W
    1.88
    V
    1.76
    S
    1.73
    F
    1.72
    B
    1.71
    C
    1.66
    X
    1.66
    E
    1.65
    H
    1.65
    J
    1.64
    Activations Density 5.453%

    No Known Activations