© 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. 77357
    Prev
    Next
    INDEX
    Explanations

    traders, users, proponents, appraisers

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

    AI workflow management

    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
    м
    0.60
    ד
    0.57
    т
    0.57
    datos
    0.56
    ר
    0.55
    к
    0.54
    MATCH
    0.53
    vred
    0.53
    р
    0.52
    טו
    0.52
    POSITIVE LOGITS
     contient
    0.53
     disparity
    0.50
     subsection
    0.49
     methionine
    0.47
     penthouse
    0.46
     possibilité
    0.46
     đang
    0.46
     existent
    0.44
     obituary
    0.44
     indicates
    0.44
    Activations Density 0.016%

    No Known Activations