© 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. 245460
    Prev
    Next
    INDEX
    Explanations

    surprise you, describe the, may be

    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
     rivel
    0.49
    等多
    0.49
     প্রভৃতি
    0.47
     überprüft
    0.47
     Regions
    0.45
     线
    0.43
     erzählt
    0.43
     preserves
    0.42
     untersucht
    0.42
    ১২শ
    0.41
    POSITIVE LOGITS
    advertising
    0.50
    athletes
    0.46
     साउंड
    0.46
    amplifier
    0.46
    ourent
    0.45
     نئے
    0.44
    ちょ
    0.44
    ା
    0.44
     अहिले
    0.43
    active
    0.43
    Activations Density 0.000%

    No Known Activations