© 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. 49248
    Prev
    Next
    INDEX
    Explanations

    date and type indicators

    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
     Amis
    -0.75
    del
    -0.75
     nostal
    -0.71
    Meh
    -0.68
     Nishi
    -0.67
     Lw
    -0.66
    انون
    -0.66
     proxim
    -0.66
    table
    -0.65
     pessi
    -0.65
    POSITIVE LOGITS
     verho
    0.68
    onium
    0.68
     third
    0.68
     адрес
    0.67
     spirit
    0.67
    tovers
    0.65
    spirit
    0.64
    第三
    0.64
    levelse
    0.63
    assador
    0.63
    Activations Density 0.076%

    No Known Activations