© 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. 10-GEMMASCOPE-RES-131K
    7. 15163
    Prev
    Next
    INDEX
    Explanations

    introducing a simple action

    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
    _
    -1.63
     ability
    -1.45
     havia
    -1.44
     waren
    -1.43
    ときに
    -1.41
     occurrence
    -1.39
    o
    -1.39
    
    -1.37
     isolada
    -1.35
     mostr
    -1.34
    POSITIVE LOGITS
     without
    1.69
    鐨
    1.58
     Like
    1.55
     as
    1.48
     or
    1.45
     with
    1.34
     alebo
    1.34
     through
    1.34
    谂
    1.33
     constaté
    1.30
    Activations Density 0.015%

    No Known Activations