© 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. 4313
    Prev
    Next
    INDEX
    Explanations

    examine, explain, why, what

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

    how can explain it

    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
    荅
    0.47
    જર
    0.46
     kül
    0.45
    BLUE
    0.44
    ROWN
    0.44
    PrivateRoute
    0.43
    Validated
    0.43
    Assassin
    0.43
    全新的
    0.43
     clockRadius
    0.43
    POSITIVE LOGITS
     Therefore
    0.84
     Why
    0.79
     Explain
    0.76
     What
    0.73
     Which
    0.72
     _____
    0.71
    嗎
    0.70
     How
    0.70
     ______
    0.69
     ಏಕೆ
    0.69
    Activations Density 0.024%

    No Known Activations