© 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. 66115
    Prev
    Next
    INDEX
    Explanations

    exterior of buildings

    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
     sensibilidad
    -1.16
    쨩
    -1.12
    uffff
    -1.11
     território
    -1.11
    čky
    -1.09
    veras
    -1.09
     caverns
    -1.08
    ileo
    -1.08
    ljiv
    -1.07
    Források
    -1.06
    POSITIVE LOGITS
     exterior
    1.61
     of
    1.29
     on
    1.22
    Exterior
    1.14
     external
    1.12
     exteriores
    1.12
     facade
    1.11
    BagLayout
    1.09
     External
    1.09
    Extern
    1.08
    Activations Density 0.037%

    No Known Activations