© 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. 91159
    Prev
    Next
    INDEX
    Explanations

    explaining books, arguments, and examples

    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
    ﺠ
    0.47
    iterator
    0.44
    ective
    0.42
    rafo
    0.42
    undaria
    0.42
    voja
    0.42
    ju
    0.42
     отмети
    0.42
     tratados
    0.42
    áctica
    0.42
    POSITIVE LOGITS
     神
    0.42
    ൃ
    0.40
     functions
    0.40
     polymer
    0.40
     m
    0.40
     computerized
    0.40
     finger
    0.39
     primitives
    0.39
     двор
    0.39
     bartenders
    0.39
    Activations Density 0.000%

    No Known Activations