© 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-262K
    7. 19222
    Prev
    Next
    INDEX
    Explanations

    database schema and coding types

    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_262k_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
    Methylsulfanyl
    0.56
    嫘
    0.54
    计时
    0.52
    Anthrop
    0.50
     Chirurg
    0.50
    治疗
    0.49
    Clin
    0.49
     Anthrop
    0.49
    彘
    0.48
    Hydrochloride
    0.47
    POSITIVE LOGITS
    null
    0.55
    fasterxml
    0.51
    export
    0.50
    financial
    0.50
    request
    0.48
    company
    0.47
    ign
    0.46
    if
    0.46
    nullable
    0.46
    knowledge
    0.46
    Activations Density 0.020%

    No Known Activations