© 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. 41502
    Prev
    Next
    INDEX
    Explanations

    casino, bar, written

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

    check: vulnerabilities, breakdown, catfight

    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
     מו
    0.54
     variegated
    0.53
     하지만
    0.52
     variational
    0.50
     효
    0.49
     ملک
    0.48
     hasht
    0.47
     imbued
    0.47
     هام
    0.46
     물
    0.46
    POSITIVE LOGITS
    3
    0.57
    ３
    0.55
    𝟯
    0.44
    Interior
    0.43
    platform
    0.42
    য়ায়
    0.41
    FolderPath
    0.41
    passport
    0.41
    MenuStyle
    0.41
     अस्थ
    0.40
    Activations Density 0.000%

    No Known Activations