© 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. 30810
    Prev
    Next
    INDEX
    Explanations

    html tags and structure

    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
     pint
    0.46
    новый
    0.42
     dentro
    0.40
     മുൻ
    0.39
     vorgesch
    0.39
     ./
    0.38
     герой
    0.38
     Rücken
    0.38
     भाई
    0.38
     Laat
    0.37
    POSITIVE LOGITS
    Depos
    0.44
    igraphy
    0.41
     bialgebras
    0.41
     कैलो
    0.40
    izma
    0.40
    mallow
    0.40
    Cour
    0.39
    adon
    0.39
    फ
    0.39
    adah
    0.39
    Activations Density 0.027%

    No Known Activations