© 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. 48906
    Prev
    Next
    INDEX
    Explanations

    consequence or sequence

    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
     impulsar
    -0.76
    waf
    -0.74
    敢
    -0.73
    marque
    -0.72
    vaní
    -0.72
     druhé
    -0.71
    kkelijk
    -0.70
    freie
    -0.68
    preg
    -0.67
    newBuilder
    -0.67
    POSITIVE LOGITS
     then
    1.55
    then
    1.35
    thenReturn
    1.31
    Then
    1.25
     Then
    0.90
     entonces
    0.89
     желание
    0.84
     dee
    0.84
     тогда
    0.84
     thì
    0.83
    Activations Density 0.002%

    No Known Activations