© 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. 59932
    Prev
    Next
    INDEX
    Explanations

    term limits

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

    connect different

    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
    只需要
    0.48
     crème
    0.46
     PROPERTIES
    0.44
     initials
    0.43
    ے
    0.42
     może
    0.41
    就会
    0.41
    कु
    0.41
     mogą
    0.41
     kawa
    0.41
    POSITIVE LOGITS
    ስማ
    0.51
    縁
    0.50
    jah
    0.49
    phill
    0.49
    mand
    0.48
     बंग
    0.47
    proces
    0.47
    rico
    0.46
    verfahren
    0.46
    riram
    0.46
    Activations Density 0.000%

    No Known Activations