© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75624
    Prev
    Next
    INDEX
    Explanations

    discussing capability and tendencies

    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
     ""),
    0.53
    ﻼ
    0.46
     общего
    0.46
    %),
    0.44
     방정식
    0.43
     бумаги
    0.43
     विश्व
    0.42
    ᱔
    0.42
    旺
    0.42
    راک
    0.41
    POSITIVE LOGITS
     അയാള
    0.49
     lids
    0.45
     harms
    0.43
    calar
    0.43
    nton
    0.42
     হেরে
    0.42
     reinforcements
    0.42
     an
    0.41
    lls
    0.41
    骯
    0.41
    Activations Density 0.002%

    No Known Activations