© 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. 34-GEMMASCOPE-RES-131K
    7. 99654
    Prev
    Next
    INDEX
    Explanations

    additions and extensions

    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_34/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
    会う
    -0.77
     agrup
    -0.76
     fortes
    -0.73
     liberate
    -0.73
    )^{-
    -0.73
     AnyObject
    -0.73
     צי
    -0.71
     assign
    -0.71
    urige
    -0.70
    地板
    -0.70
    POSITIVE LOGITS
     extensions
    3.06
     extension
    2.98
     additions
    2.70
     addition
    2.56
    extension
    2.55
     Extensions
    2.41
    extensions
    2.33
     Extension
    2.28
    Extensions
    2.20
    Extension
    2.06
    Activations Density 0.028%

    No Known Activations