© 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. 50255
    Prev
    Next
    INDEX
    Explanations

    mathematics, reason, justification, combining

    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
    ha
    0.48
     biological
    0.47
    ∈
    0.46
    śred
    0.46
     संस्कृति
    0.46
     pulmon
    0.46
    extrémité
    0.45
     forment
    0.45
    plaat
    0.45
    caso
    0.45
    POSITIVE LOGITS
    itec
    0.42
    antle
    0.41
     writs
    0.39
    ﾘ
    0.38
    ксана
    0.38
     pria
    0.38
    awas
    0.37
    axel
    0.37
    bq
    0.37
    #-
    0.37
    Activations Density 0.000%

    No Known Activations