© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79888
    Prev
    Next
    INDEX
    Explanations

    guided differentiation

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

    numerical statistics and data in sports and academic contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kript
    -0.97
    我知道
    -0.96
    まずは
    -0.94
     huur
    -0.93
    अप
    -0.93
     simply
    -0.92
     utente
    -0.91
     ſuch
    -0.90
    ありがとうございました
    -0.89
    setcounter
    -0.89
    POSITIVE LOGITS
     last
    1.26
     since
    1.24
     bislang
    1.16
     erstmals
    1.04
    geoning
    1.03
    惬
    1.02
     senaste
    1.01
     depuis
    1.00
     vs
    0.99
     aldri
    0.96
    Activations Density 0.013%

    No Known Activations