© 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. 108343
    Prev
    Next
    INDEX
    Explanations

    specific methods described

    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
    !***
    -0.82
    yness
    -0.78
    tissa
    -0.75
    boiler
    -0.75
    ovatel
    -0.75
    upe
    -0.73
    Pranala
    -0.73
     deberían
    -0.71
    фер
    -0.71
    тип
    -0.71
    POSITIVE LOGITS
     method
    6.53
     methods
    5.00
    method
    4.47
     Method
    4.31
     método
    4.28
    方法
    4.22
    Method
    4.13
     méthode
    4.06
    METHOD
    4.03
     METHOD
    3.94
    Activations Density 0.398%

    No Known Activations