© 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-262K
    7. 23118
    Prev
    Next
    INDEX
    Explanations

    De Broglie's, Indirect Discrimination, intrapreneurship

    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
     estómago
    0.42
    ர
    0.41
    burgo
    0.40
    ей
    0.40
    oscow
    0.39
    冈
    0.39
     Viele
    0.39
     곡
    0.39
     zegt
    0.39
     barrels
    0.38
    POSITIVE LOGITS
    4
    0.55
    Survived
    0.52
     procesu
    0.48
     Emerg
    0.47
    ための
    0.47
    の声
    0.46
    ките
    0.46
     validations
    0.45
     emergencies
    0.44
     entw
    0.44
    Activations Density 0.002%

    No Known Activations