© 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. 223921
    Prev
    Next
    INDEX
    Explanations

    familiar with training seminar

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

    programming and ASMR content

    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
     Savings
    0.49
    冰
    0.48
     savings
    0.45
    行为
    0.45
     Upon
    0.43
     Salv
    0.43
     Saved
    0.43
    贫
    0.43
     Prayer
    0.43
     CALL
    0.43
    POSITIVE LOGITS
     foreseen
    0.47
     interposed
    0.46
    ලා
    0.43
     unduly
    0.42
     incó
    0.42
    istage
    0.42
    ponential
    0.42
    coefficient
    0.41
     breaching
    0.41
     توسیع
    0.40
    Activations Density 0.001%

    No Known Activations