© 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. 122829
    Prev
    Next
    INDEX
    Explanations

    selecting options or rewards

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

    size, topics, lengths, Android

    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
     acronym
    0.51
    ϵ
    0.45
     is
    0.44
     refrained
    0.44
    ಟಿ
    0.42
    кти
    0.42
     spared
    0.41
     cultured
    0.41
     EXPL
    0.41
     rallied
    0.40
    POSITIVE LOGITS
    ellingen
    0.49
     куп
    0.47
    emper
    0.46
     Witnesses
    0.44
    䂺
    0.44
     sparsim
    0.44
    蛉
    0.43
     Shaping
    0.43
     setor
    0.43
     Тут
    0.42
    Activations Density 0.000%

    No Known Activations