© 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. 190403
    Prev
    Next
    INDEX
    Explanations

    to watch or check

    np_acts-logits-general · gemini-2.5-flash-lite

    responsible AI development

    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
     docentes
    0.49
     Economics
    0.48
     پوری
    0.46
    ਤਰ
    0.46
    孫
    0.45
    AM
    0.45
     deux
    0.44
    児童
    0.44
    өрү
    0.44
     ។
    0.44
    POSITIVE LOGITS
    лизация
    0.46
     imitated
    0.44
     cramps
    0.44
     keram
    0.42
     screwed
    0.42
     sphing
    0.42
    特殊的
    0.41
    versch
    0.41
     autoimmunity
    0.41
     secretly
    0.40
    Activations Density 0.000%

    No Known Activations