© 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. 13887
    Prev
    Next
    INDEX
    Explanations

    exam practice pdf

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

    malicious code or attacks

    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
     ஐந்து
    0.43
    ূন্য
    0.42
     micrograms
    0.42
     fillColorSpace
    0.41
     रिपीट
    0.40
     trataro
    0.39
     organique
    0.39
    缙
    0.39
    geoType
    0.39
    䏍
    0.39
    POSITIVE LOGITS
     FEM
    0.48
     Mark
    0.41
     Рі
    0.41
    Fem
    0.40
     ¿
    0.40
    Psalm
    0.40
    FEM
    0.39
     Μ
    0.39
     Yeh
    0.39
     Fey
    0.39
    Activations Density 0.000%

    No Known Activations