© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34399
    Prev
    Next
    INDEX
    Explanations

    Retrieved

    np_acts-logits-general · gemini-2.5-flash-lite

    gaining visibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    và
    0.55
    και
    0.53
    Portugal
    0.53
     અને
    0.52
     Và
    0.51
    Otro
    0.51
    Secondo
    0.50
    男
    0.50
    le
    0.50
    Vill
    0.49
    POSITIVE LOGITS
     osmosis
    0.54
     lectures
    0.50
     enlightened
    0.50
     deserted
    0.50
     audiovisual
    0.48
     barric
    0.48
     dinner
    0.47
     carbohydrates
    0.47
     orchestra
    0.46
     Ashram
    0.46
    Activations Density 0.000%

    No Known Activations