© 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. 235030
    Prev
    Next
    INDEX
    Explanations

    cold sores

    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
     compuls
    0.52
    »)
    0.49
     interven
    0.48
     +#+
    0.47
    гно
    0.46
     mislead
    0.46
     aband
    0.46
    )».
    0.45
     %)
    0.44
    вига
    0.44
    POSITIVE LOGITS
    тических
    0.47
     Law
    0.46
    <0xE7>
    0.45
    两个
    0.44
    保险
    0.44
     Applicants
    0.43
    <0xE5>
    0.43
     Safety
    0.43
     Training
    0.43
    set
    0.42
    Activations Density 0.000%

    No Known Activations