© 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. 34073
    Prev
    Next
    INDEX
    Explanations

    finding 'int' and 'self'

    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
    開設
    -1.03
    そのため
    -1.01
    ですが
    -0.99
    ｽ
    -0.96
    だが
    -0.96
    櫚
    -0.93
    一样的
    -0.93
    靼
    -0.93
     CGPoint
    -0.92
     동안
    -0.91
    POSITIVE LOGITS
    ",
    1.12
     ondas
    1.06
    </th>
    1.00
    ="+
    0.98
     Campionato
    0.97
    来週
    0.96
    他又
    0.95
    ',
    0.94
    "},
    0.94
     warunki
    0.94
    Activations Density 0.005%

    No Known Activations