© 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. 134709
    Prev
    Next
    INDEX
    Explanations

    Israel, Lost, imposed

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

    indicating power, networking, startup, rays

    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
    ız
    0.50
     депозит
    0.49
    이나
    0.47
     നിന്നും
    0.45
    ımızın
    0.45
    lular
    0.45
    ꧂
    0.44
    nage
    0.43
    ගේ
    0.43
    ınızı
    0.42
    POSITIVE LOGITS
     remod
    0.48
     referenties
    0.48
     Lees
    0.47
     informatique
    0.47
    ;"
    0.44
    exports
    0.44
     renov
    0.44
     municipalities
    0.43
     tunable
    0.42
     Acquisitions
    0.42
    Activations Density 0.001%

    No Known Activations