© 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. 39881
    Prev
    Next
    INDEX
    Explanations

    suitable material or kind

    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
    
    -1.85
     kategor
    -1.68
    jetzt
    -1.67
    ##
    -1.63
    Теперь
    -1.63
    sehr
    -1.55
     kupa
    -1.55
    
    -1.54
     klinik
    -1.54
    essentially
    -1.53
    POSITIVE LOGITS
     or
    1.88
     with
    1.80
     be
    1.75
     such
    1.74
     is
    1.67
     или
    1.61
     other
    1.58
     if
    1.55
     another
    1.49
     those
    1.46
    Activations Density 0.143%

    No Known Activations