© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1477
    Prev
    Next
    INDEX
    Explanations

    how things differ

    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
     Фі
    0.68
     Ε
    0.67
     عمر
    0.66
     מל
    0.64
    aient
    0.64
    后续
    0.63
     مُ
    0.62
     mante
    0.62
     Fix
    0.61
     фі
    0.61
    POSITIVE LOGITS
    ໑
    0.71
    LE
    0.70
    হেতু
    0.69
    ченный
    0.69
    ZONE
    0.69
     scuba
    0.69
    GHz
    0.68
    hundred
    0.68
     сайты
    0.67
    Apex
    0.67
    Activations Density 0.007%

    No Known Activations