© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10821
    Prev
    Next
    INDEX
    Explanations

    behind phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.91
     BE
    0.87
    edes
    0.85
    BE
    0.85
    ence
    0.83
    '
    0.83
     genre
    0.78
     limite
    0.77
     euro
    0.76
     мес
    0.76
    POSITIVE LOGITS
     الاد
    0.89
     pertenec
    0.86
    <unused46>
    0.86
    ματα
    0.85
     RARRAY
    0.82
     administrativas
    0.82
     amacıyla
    0.81
     cuyas
    0.80
    刧
    0.79
    ского
    0.79
    Activations Density 0.000%

    No Known Activations