© 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. 92228
    Prev
    Next
    INDEX
    Explanations

    after + noun

    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
    別の
    -0.83
     sparing
    -0.82
    ينج
    -0.76
    什么事
    -0.75
    それでは
    -0.73
     composite
    -0.72
     reliance
    -0.71
    Y
    -0.71
    in
    -0.70
    enne
    -0.69
    POSITIVE LOGITS
    burner
    1.46
    glow
    1.30
    effects
    1.29
    thoughts
    1.25
    thought
    1.25
    care
    1.22
    taste
    1.16
    math
    1.15
    effect
    1.12
    shock
    1.12
    Activations Density 0.020%

    No Known Activations