© 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. 34-GEMMASCOPE-RES-131K
    7. 92692
    Prev
    Next
    INDEX
    Explanations

    as as possible

    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
    Available
    -1.59
    available
    -1.55
     Available
    -1.41
    Availability
    -1.33
     Availability
    -1.27
     AVAILABLE
    -1.23
    AVAILABLE
    -1.11
    availability
    -1.09
    Unavailable
    -1.04
    Applicable
    -1.02
    POSITIVE LOGITS
     possible
    1.77
     potential
    1.00
     가능
    0.98
     mogelijk
    0.96
     möjligt
    0.94
     можли
    0.93
    bish
    0.87
    可能的
    0.86
    有什麼
    0.86
    憤
    0.86
    Activations Density 0.055%

    No Known Activations