© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202980
    Prev
    Next
    INDEX
    Explanations

    legal and formal terms

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

    general knowledge, mathematics, and descriptions

    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
     deinem
    0.47
     visant
    0.46
    
    0.46
     obje
    0.46
    ിയി
    0.45
     okula
    0.45
     plonge
    0.44
     pouvant
    0.44
    幼儿
    0.44
     entornos
    0.44
    POSITIVE LOGITS
    therners
    0.45
     thio
    0.45
    ck
    0.45
    balance
    0.45
    ssr
    0.45
    factor
    0.44
    ñ
    0.44
     সমাপ্ত
    0.44
    =[-
    0.44
    blues
    0.43
    Activations Density 0.000%

    No Known Activations