© 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. 108356
    Prev
    Next
    INDEX
    Explanations

    casual

    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
    装飾
    -0.96
     alemão
    -0.93
     negocia
    -0.91
     Somebody
    -0.90
     silêncio
    -0.88
    ötä
    -0.86
     chefe
    -0.84
    rugs
    -0.84
     mitigated
    -0.84
    ackerel
    -0.84
    POSITIVE LOGITS
     casual
    1.44
    casual
    1.27
     but
    1.21
     Fridays
    1.20
     Casual
    1.16
    Casual
    1.14
     causal
    1.13
     chic
    1.11
     acquaintance
    1.11
     elegance
    1.05
    Activations Density 0.010%

    No Known Activations