© 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. 10375
    Prev
    Next
    INDEX
    Explanations

    its core / its heart

    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
    .
    0.85
    ih
    0.78
     subterr
    0.76
    збе
    0.72
     beetles
    0.71
    ü
    0.70
     Working
    0.70
    mr
    0.70
     local
    0.69
    ense
    0.68
    POSITIVE LOGITS
    ه
    0.98
    ה
    0.91
    Así
    0.88
     mauvais
    0.86
     kesan
    0.85
     kemudian
    0.82
    トップ
    0.82
     المعادله
    0.82
    Bike
    0.82
     важли
    0.81
    Activations Density 0.000%

    No Known Activations