© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6678
    Prev
    Next
    INDEX
    Explanations

    enroll multiple fingerprints (at least 5-7 is a good target)

    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_31_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
    F
    0.79
    Y
    0.78
    Z
    0.77
    ON
    0.76
    Od
    0.75
    Ok
    0.75
    犮
    0.75
    aturally
    0.74
    E
    0.73
     Omphalodes
    0.71
    POSITIVE LOGITS
     стоят
    0.86
     hustle
    0.83
     hangout
    0.82
     asta
    0.79
     outdoor
    0.78
     procrastination
    0.77
     leve
    0.76
     chcesz
    0.76
     HVAC
    0.76
     prez
    0.75
    Activations Density 0.054%

    No Known Activations