© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72955
    Prev
    Next
    INDEX
    Explanations

    lists separated by commas or 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     then
    -1.26
    ございました
    -1.19
     voorwaarden
    -1.09
     nochmal
    -1.09
     penyimpanan
    -1.08
     leeftijd
    -1.08
     studia
    -1.07
    雖
    -1.07
     trattano
    -1.06
    Ų
    -1.06
    POSITIVE LOGITS
    rentices
    1.09
    果汁
    1.00
    pirable
    0.99
    postsleuth
    0.99
     research
    0.98
    endalikan
    0.98
    <bos>
    0.98
    福建
    0.95
     المثال
    0.95
     его
    0.94
    Activations Density 0.060%

    No Known Activations