© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68869
    Prev
    Next
    INDEX
    Explanations

    names followed by possessive or description

    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
     того
    -1.10
    logIn
    -1.02
     itself
    -0.99
     that
    -0.98
     bisogno
    -0.97
    0
    -0.95
     бере
    -0.94
    は
    -0.93
    They
    -0.93
    というと
    -0.93
    POSITIVE LOGITS
     himself
    1.82
     his
    1.70
    himself
    1.52
    ův
    1.23
    他的
    1.16
     그의
    1.10
     himſelf
    1.09
    pravy
    1.08
    RIK
    1.06
    ’
    1.06
    Activations Density 0.044%

    No Known Activations