© 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. 18348
    Prev
    Next
    INDEX
    Explanations

    flow of things

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

    flow of

    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
    ן
    0.68
    are
    0.63
    antal
    0.59
    eneration
    0.59
    roph
    0.56
    िन
    0.56
    он
    0.56
    iguation
    0.56
    itz
    0.55
    opaedic
    0.54
    POSITIVE LOGITS
     flow
    1.75
    Flow
    1.63
     Flow
    1.61
    FLOW
    1.59
    flow
    1.58
    流
    1.55
     flows
    1.55
     FLOW
    1.43
     Flows
    1.42
     flowed
    1.40
    Activations Density 0.079%

    No Known Activations