© 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. 34033
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or slashes

    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
     and
    -2.25
    の方に
    -2.25
     farba
    -2.13
    閹
    -2.11
    corrhi
    -2.02
     olvid
    -2.00
     reprezenta
    -1.97
    部に
    -1.97
     desbloquear
    -1.97
    に行って
    -1.92
    POSITIVE LOGITS
    ↵
    3.88
    n
    2.66
    d
    2.28
    m
    2.27
    al
    2.09
    c
    2.09
    b
    2.06
    t
    2.03
    がある
    1.99
    
    1.98
    Activations Density 0.218%

    No Known Activations