© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51885
    Prev
    Next
    INDEX
    Explanations

    disclaimers, toxic content, delays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻬ
    0.48
    வதன்
    0.45
     littérature
    0.45
     Comunidad
    0.44
     frequentemente
    0.43
     herramienta
    0.43
     universidad
    0.43
    वालों
    0.42
     lengua
    0.42
    燴
    0.42
    POSITIVE LOGITS
    ⚡
    0.50
    😢
    0.50
     $'
    0.48
    minimum
    0.48
    minimal
    0.47
    were
    0.46
    😬
    0.46
    st
    0.45
    ।
    0.45
    📜
    0.45
    Activations Density 0.004%

    No Known Activations