© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107573
    Prev
    Next
    INDEX
    Explanations

    fog and foggy conditions

    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
    PREFERRED
    -0.77
    relax
    -0.75
    Coral
    -0.73
     quivering
    -0.72
    pul
    -0.72
     windmill
    -0.72
    Avoid
    -0.72
    Wind
    -0.72
     ауди
    -0.72
    cioso
    -0.71
    POSITIVE LOGITS
     fog
    3.81
    fog
    2.88
     Fog
    2.84
    Fog
    2.83
     foggy
    2.70
     mist
    2.39
    雾
    2.17
     niebla
    2.14
     FOG
    2.05
    霧
    2.05
    Activations Density 0.027%

    No Known Activations