© 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. 9443
    Prev
    Next
    INDEX
    Explanations

    tightness, tight, and related concepts

    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
    ActionMode
    2.09
    ม
    2.02
     destiné
    2.00
    क
    2.00
    િ
    2.00
    ک
    1.95
     prévue
    1.91
    ิ
    1.89
     μία
    1.88
     arrondie
    1.87
    POSITIVE LOGITS
    el
    2.72
    al
    2.50
    t
    2.28
    un
    2.13
    g
    1.91
    سون
    1.91
    s
    1.90
    ab
    1.83
    en
    1.82
    az
    1.80
    Activations Density 0.060%

    No Known Activations