© 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. 65847
    Prev
    Next
    INDEX
    Explanations

    introduces with 'Interestingly',

    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
    ){\
    -1.37
     what
    -1.31
     enten
    -1.27
     bagaimana
    -1.27
    ScopeManager
    -1.27
    isait
    -1.26
    ++)
    -1.25
    )<<
    -1.24
    }}}{\
    -1.23
    __":
    -1.22
    POSITIVE LOGITS
     also
    1.98
     though
    1.48
     גם
    1.35
     only
    1.33
     never
    1.29
     however
    1.29
    also
    1.27
     even
    1.27
     neither
    1.25
    albeit
    1.24
    Activations Density 0.020%

    No Known Activations