© 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. 121655
    Prev
    Next
    INDEX
    Explanations

    Which is comparison

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

    animated, English, fur, wing

    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
     dozen
    0.47
     constituent
    0.44
     schizophren
    0.44
     séparation
    0.43
     viens
    0.42
     ď
    0.42
     materia
    0.42
     pavement
    0.42
     narcot
    0.41
     checklist
    0.41
    POSITIVE LOGITS
     уйнау
    0.47
    弑
    0.46
     isometry
    0.44
     गोपाल
    0.44
    erche
    0.43
    ling
    0.42
    得了
    0.42
    伟
    0.42
    ti
    0.42
    endering
    0.42
    Activations Density 0.001%

    No Known Activations