© 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. 10-GEMMASCOPE-RES-131K
    7. 65873
    Prev
    Next
    INDEX
    Explanations

    regular expressions, anchors, or separators

    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_10/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
    '
    -1.92
     they
    -1.81
     
    -1.52
     one
    -1.49
    hedrals
    -1.49
    ing
    -1.47
    feld
    -1.46
     Some
    -1.45
    ומית
    -1.45
     –
    -1.45
    POSITIVE LOGITS
    arım
    1.77
     tył
    1.75
     ganzes
    1.73
    ᐠ
    1.72
    ꜆
    1.71
     };
    1.67
    注意事
    1.64
     solches
    1.63
     саме
    1.63
    anın
    1.61
    Activations Density 0.004%

    No Known Activations