© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51897
    Prev
    Next
    INDEX
    Explanations

    sharing and context

    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_40_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
    ீர
    0.39
    ')[
    0.39
     depiction
    0.38
    ocard
    0.38
    ﻚ
    0.38
    nment
    0.38
     ヘア
    0.37
     Shee
    0.37
     اسٹی
    0.37
    ﻷ
    0.37
    POSITIVE LOGITS
    unta
    0.46
    âr
    0.41
    resse
    0.37
    anity
    0.37
    head
    0.36
    CCS
    0.36
     동시에
    0.36
    bottom
    0.35
    েবের
    0.35
    เชิง
    0.35
    Activations Density 0.013%

    No Known Activations