© 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. 108104
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
     etc
    -0.85
    rimidine
    -0.85
    etc
    -0.81
    therosclerosis
    -0.80
    ങ്ങൾ
    -0.80
    참
    -0.80
     или
    -0.79
    ⊢
    -0.77
    를
    -0.77
     при
    -0.77
    POSITIVE LOGITS
     key
    0.87
     rempli
    0.86
     getKey
    0.85
     démission
    0.84
     délais
    0.84
     clés
    0.83
    ,
    0.81
     seventies
    0.80
    しまいました
    0.79
    barb
    0.79
    Activations Density 0.021%

    No Known Activations