© 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. 12053
    Prev
    Next
    INDEX
    Explanations

    road directions and locations

    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
    >\<^
    0.43
     \%
    0.36
     dechlorination
    0.35
     ကျွန်
    0.35
     ሌሎች
    0.34
     compréhension
    0.33
    📻
    0.32
     أحد
    0.32
     בין
    0.32
     dalších
    0.32
    POSITIVE LOGITS
    c
    0.41
    k
    0.38
    v
    0.38
    san
    0.38
    ar
    0.38
    i
    0.37
    ﻛ
    0.37
    ta
    0.37
    src
    0.37
    sur
    0.37
    Activations Density 0.007%

    No Known Activations