© 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. 39896
    Prev
    Next
    INDEX
    Explanations

    mission in Western Sahara

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

    dice, META, inches, band

    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
    엄
    0.52
    栢
    0.51
    二年
    0.47
     Старки
    0.46
    ចែក
    0.46
     اللّه
    0.46
    较低
    0.46
     उत्तरी
    0.46
     Timurtaş
    0.45
    원을
    0.45
    POSITIVE LOGITS
    VO
    0.46
    ugu
    0.46
    uz
    0.45
    '].
    0.45
     replay
    0.45
     bunny
    0.44
    .
    0.44
    onResume
    0.43
     pickup
    0.43
    swim
    0.43
    Activations Density 0.000%

    No Known Activations