© 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. 100953
    Prev
    Next
    INDEX
    Explanations

    evening scientific panel fasting

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

    resources, Serialize, sources

    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
     meriye
    0.67
    రెడ్డి
    0.59
     нови
    0.55
    밂
    0.55
     incênd
    0.50
     инду
    0.50
     фарма
    0.49
     الايه
    0.49
     מר
    0.49
    ющи
    0.49
    POSITIVE LOGITS
    al
    0.65
    end
    0.55
    res
    0.54
    ↵↵
    0.52
    _
    0.51
    ers
    0.50
    ang
    0.50
    d
    0.48
    yn
    0.48
    il
    0.47
    Activations Density 0.000%

    No Known Activations