© 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. 34443
    Prev
    Next
    INDEX
    Explanations

    short end of the stick

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

    AI development prerequisites

    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
    extré
    0.54
    ądź
    0.49
    薩
    0.49
    getRadius
    0.48
    ADO
    0.48
    טים
    0.48
    geolocation
    0.48
    espère
    0.48
    ತ್ರಿ
    0.47
    Ű
    0.47
    POSITIVE LOGITS
     Resting
    0.52
     Devils
    0.42
     Pork
    0.42
     rests
    0.41
     Residences
    0.41
     उर्फ
    0.40
     WAT
    0.40
     ([
    0.39
    ,*
    0.39
     Perkin
    0.39
    Activations Density 0.000%

    No Known Activations