© 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-65K
    7. 55182
    Prev
    Next
    INDEX
    Explanations

    calculates connects finishes

    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
    ка
    0.50
    дового
    0.46
    価
    0.45
     erro
    0.45
    價值
    0.44
    ேன்
    0.43
    תי
    0.43
    اره
    0.42
     profilo
    0.41
    лым
    0.41
    POSITIVE LOGITS
     打开
    0.50
    passwd
    0.47
    运营
    0.46
    ﻯ
    0.45
     wikiHow
    0.45
     адво
    0.45
     गंभीर
    0.44
    Wir
    0.44
    uwen
    0.43
    reporter
    0.43
    Activations Density 0.006%

    No Known Activations