© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242343
    Prev
    Next
    INDEX
    Explanations

    warnings, don't, first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    separ
    0.46
    !</
    0.45
     separated
    0.44
    ODBA
    0.44
    ប្ប
    0.44
    !'
    0.44
    يمكن
    0.44
     निश्च
    0.43
     recibir
    0.43
    adka
    0.43
    POSITIVE LOGITS
     Warning
    0.44
     Jangan
    0.42
     eerst
    0.42
    ాలపై
    0.41
    다면
    0.40
     jangan
    0.40
    鳜
    0.40
     dulu
    0.40
    ినా
    0.39
     Classroom
    0.39
    Activations Density 0.000%

    No Known Activations