© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47188
    Prev
    Next
    INDEX
    Explanations

    oddly smooth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ທີ່ມີ
    0.45
    𝙥
    0.43
     customizable
    0.43
     plausible
    0.43
     draggable
    0.42
     scalable
    0.42
     Preferably
    0.42
    ウム
    0.42
     centimetres
    0.42
     extensible
    0.41
    POSITIVE LOGITS
    ?
    0.52
    dyž
    0.45
    oty
    0.44
    leman
    0.43
    zellen
    0.43
    z
    0.43
     folgende
    0.42
     சொல்க
    0.41
    arn
    0.41
    doc
    0.40
    Activations Density 0.007%

    No Known Activations