© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5086
    Prev
    Next
    INDEX
    Explanations

    items and concepts

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

    concerns and requirements

    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
     of
    0.30
     be
    0.26
    牫
    0.26
     de
    0.24
    ik
    0.24
    ല്
    0.24
    _)
    0.23
     එය
    0.23
    ographical
    0.23
    겠지만
    0.23
    POSITIVE LOGITS
     extraordinaire
    0.32
     також
    0.30
     cũng
    0.29
     tambien
    0.28
     również
    0.28
     смотрите
    0.26
    에서도
    0.26
    штейн
    0.26
     επίσης
    0.26
    сах
    0.25
    Activations Density 1.632%

    No Known Activations