© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197654
    Prev
    Next
    INDEX
    Explanations

    waste disposal and contractors

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that lead to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    н
    0.54
    бар
    0.50
    ین
    0.47
    сед
    0.46
    б
    0.45
     रस
    0.43
    ন
    0.43
    лт
    0.42
    ட்
    0.42
    лат
    0.42
    POSITIVE LOGITS
     understated
    0.52
     เหรอ
    0.48
     있고
    0.47
    িলারা
    0.47
     consented
    0.45
     muttered
    0.45
     attendee
    0.45
     😊
    0.44
     clipped
    0.43
     attend
    0.43
    Activations Density 0.000%

    No Known Activations