© 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. 145523
    Prev
    Next
    INDEX
    Explanations

    professional repairs condition

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

    mention a, manufacturing, might wear, Bobby Fischer, provide

    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
     mixtures
    0.52
    ضه
    0.50
     metaphors
    0.48
     \<
    0.48
     constipation
    0.48
    sections
    0.47
     dort
    0.46
     oración
    0.46
    닌
    0.46
     uptake
    0.46
    POSITIVE LOGITS
    unca
    0.43
    箜
    0.42
     зат
    0.42
    óc
    0.41
     expressly
    0.40
    يس
    0.39
    欸
    0.39
    <0x9C>
    0.39
    '
    0.39
    瞽
    0.39
    Activations Density 0.000%

    No Known Activations