© 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. 22-GEMMASCOPE-RES-131K
    7. 26091
    Prev
    Next
    INDEX
    Explanations

    numbers ± symbols % years

    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_22/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
     because
    -1.05
     egentlig
    -1.05
    文分享
    -0.99
    धारण
    -0.96
     છ
    -0.96
     understand
    -0.95
     melainkan
    -0.93
    intervento
    -0.91
     sufficient
    -0.91
     not
    -0.91
    POSITIVE LOGITS
     captiv
    0.97
    ipal
    0.90
     biedt
    0.90
     ardu
    0.89
     ……
    0.89
     …..
    0.86
    pav
    0.86
     Leads
    0.85
     tuss
    0.85
    brio
    0.84
    Activations Density 0.018%

    No Known Activations