© 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. 165935
    Prev
    Next
    INDEX
    Explanations

    purpose of development, company negotiations, emails within hours

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

    Mapping, more about, relevant pre

    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
     През
    0.50
     Curse
    0.47
     ngon
    0.46
     t
    0.46
    ‚
    0.45
     Apro
    0.44
    (";
    0.44
     rese
    0.44
    iança
    0.44
     lojas
    0.44
    POSITIVE LOGITS
    ธิบาย
    0.46
    শি
    0.44
    ーリー
    0.44
    тельных
    0.43
    ρν
    0.42
     streamwise
    0.41
    숱
    0.41
     lubricant
    0.41
    ਰ
    0.41
    スイッチ
    0.40
    Activations Density 0.000%

    No Known Activations