© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130045
    Prev
    Next
    INDEX
    Explanations

    programming function declarations

    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
    сында
    -1.09
     riusc
    -1.02
     -
    -0.99
     rispond
    -0.98
     "
    -0.94
     aggiun
    -0.94
     تلك
    -0.94
     entschieden
    -0.94
    !/
    -0.93
    agosto
    -0.93
    POSITIVE LOGITS
     which
    1.18
     at
    1.16
     字体
    1.07
     naszego
    1.06
    jemah
    1.02
     our
    1.02
     maybe
    1.00
    ambung
    0.99
    ZAM
    0.99
     или
    0.98
    Activations Density 0.005%

    No Known Activations