© 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. 38683
    Prev
    Next
    INDEX
    Explanations

    code commands and names

    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
     technisch
    -1.05
    ESTON
    -1.01
     Galería
    -0.99
    ový
    -0.95
     indescri
    -0.94
     gemeenten
    -0.94
    ществует
    -0.94
    攥
    -0.94
     aking
    -0.94
     rémun
    -0.94
    POSITIVE LOGITS
     not
    1.24
     to
    1.22
     that
    1.15
     good
    1.13
     want
    1.13
    濯
    1.12
     from
    1.07
    詐
    1.07
     any
    1.06
     tot
    1.06
    Activations Density 0.034%

    No Known Activations