© 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. 72757
    Prev
    Next
    INDEX
    Explanations

    fly catch, responsiveness, RaZe Gaming

    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
    kimono
    -1.09
    ⟢
    -1.09
    hijab
    -1.09
     hırka
    -1.08
     paisagem
    -1.08
     tunik
    -1.07
    有難
    -1.07
     菇
    -1.06
    camis
    -1.05
    crocs
    -1.05
    POSITIVE LOGITS
    P
    1.09
    M
    1.03
    :
    1.01
    r
    0.99
    p
    0.96
    h
    0.96
    R
    0.96
    T
    0.95
     Strecken
    0.92
    n
    0.92
    Activations Density 0.079%

    No Known Activations