© 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. 72135
    Prev
    Next
    INDEX
    Explanations

    places or where entities are

    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
     ТАК
    -1.37
     their
    -1.16
     majeurs
    -1.14
    Struktur
    -1.13
     that
    -1.12
    看起來
    -1.08
     artikelen
    -1.08
    他們的
    -1.08
     ugli
    -1.06
     بزر
    -1.05
    POSITIVE LOGITS
    での
    1.19
     was
    1.16
     experience
    1.11
    issä
    1.08
    where
    1.04
     estadia
    1.03
    에서
    1.02
     instituição
    1.02
    uu
    1.00
     حيث
    0.99
    Activations Density 0.027%

    No Known Activations