© 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. 156816
    Prev
    Next
    INDEX
    Explanations

    time and suspicion

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

    elephant jokes

    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
    هم
    0.57
    </
    0.47
    <0xAF>
    0.47
    </strong>
    0.46
    英語
    0.46
     Calculus
    0.46
    وار
    0.44
     Dual
    0.44
     bark
    0.43
    Bark
    0.43
    POSITIVE LOGITS
    탰
    0.53
     thermocouple
    0.52
     여기에
    0.52
    ದಾರ
    0.50
    $=
    0.49
     arrêté
    0.48
     ķ
    0.47
    元件
    0.46
     chhoti
    0.46
    Externe
    0.46
    Activations Density 0.000%

    No Known Activations