© 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. 202144
    Prev
    Next
    INDEX
    Explanations

    guide will walk you through

    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
    ಮ
    0.54
    ઙ
    0.51
    ım
    0.47
     regola
    0.45
     corred
    0.44
    R
    0.43
    prescription
    0.43
    ುತ್ತಿರುವ
    0.42
     meaty
    0.42
    ברת
    0.42
    POSITIVE LOGITS
    TableHeader
    0.46
    🐯
    0.45
     którego
    0.44
     تۆ
    0.43
    ply
    0.43
     captured
    0.43
    🤵
    0.43
     তুমি
    0.43
     hottest
    0.43
     rhet
    0.42
    Activations Density 0.000%

    No Known Activations