© 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-262K
    7. 41867
    Prev
    Next
    INDEX
    Explanations

    prompt to attention

    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
    ي
    1.43
    y
    1.34
    ি
    1.27
    ल
    1.19
    י
    1.16
    RA
    1.15
    L
    1.13
    D
    1.11
    MER
    1.09
    MENTS
    1.07
    POSITIVE LOGITS
    ни
    1.03
     оказывается
    0.91
     índices
    0.88
     metavar
    0.86
     deja
    0.83
     tẩy
    0.82
    ній
    0.80
     כי
    0.80
     ris
    0.80
     pati
    0.79
    Activations Density 0.000%

    No Known Activations