© 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. 111442
    Prev
    Next
    INDEX
    Explanations

    topics and facts

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

    ROI, love, defensive

    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
    РО
    0.52
    С
    0.50
    ukawa
    0.48
    П
    0.48
    보
    0.48
    РИ
    0.46
     BON
    0.46
    എ
    0.46
    які
    0.45
    黯
    0.45
    POSITIVE LOGITS
     Junior
    0.48
     reigning
    0.45
     Defensive
    0.42
     Equals
    0.42
     Defense
    0.42
     Defendant
    0.40
    .,
    0.40
     externe
    0.40
    @",
    0.40
     Acting
    0.39
    Activations Density 0.002%

    No Known Activations