© 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. 199635
    Prev
    Next
    INDEX
    Explanations

    blog, exposed, persuasive, probability

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

    potentially occurring artificially

    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
     TreeNode
    0.48
    jük
    0.48
    飕
    0.47
     tables
    0.47
    сте
    0.46
     crayon
    0.45
    leşt
    0.45
    harris
    0.44
     texte
    0.44
     spatula
    0.44
    POSITIVE LOGITS
     eradicated
    0.47
    ఔ
    0.46
     safeguards
    0.45
     पहुंचाया
    0.45
     persists
    0.44
    That
    0.44
    サン
    0.44
     کیشن
    0.44
    アシ
    0.43
    珍
    0.43
    Activations Density 0.000%

    No Known Activations