© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77355
    Prev
    Next
    INDEX
    Explanations

    historical reputation

    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
    los
    0.48
     (=
    0.44
    öffentlich
    0.43
    comics
    0.42
     freezes
    0.42
    sweet
    0.42
     insign
    0.42
     badges
    0.42
    rockets
    0.42
    tene
    0.41
    POSITIVE LOGITS
     aasta
    0.43
    ᓱ
    0.43
     LIE
    0.42
    ปี
    0.42
    Year
    0.41
     pinta
    0.41
     үшін
    0.40
    萦
    0.40
    证明
    0.40
    われて
    0.39
    Activations Density 0.003%

    No Known Activations