© 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. 26752
    Prev
    Next
    INDEX
    Explanations

    AVG sqlite queries and roles

    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
     vieta
    -1.11
    })).
    -0.93
     туа
    -0.89
     Hull
    -0.88
    ┈
    -0.88
    ɡ
    -0.87
     my
    -0.85
     kriti
    -0.85
     geogra
    -0.85
    ℉
    -0.84
    POSITIVE LOGITS
    lazione
    1.00
     Ă
    0.90
     erzielt
    0.88
     Guests
    0.81
    rits
    0.81
     Megal
    0.80
     profundidad
    0.79
     sostenibilidad
    0.78
     ‹
    0.78
     THROUGH
    0.77
    Activations Density 0.175%

    No Known Activations