© 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. 41069
    Prev
    Next
    INDEX
    Explanations

    quantifying information

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

    results approximately

    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
    yout
    0.45
    มัน
    0.45
    ραι
    0.45
    rfloor
    0.44
    uffling
    0.43
    它可以
    0.43
    ONOM
    0.43
    t
    0.42
    dedicated
    0.40
    inverted
    0.40
    POSITIVE LOGITS
    乆
    0.45
    cuits
    0.42
    źdz
    0.41
    ىم
    0.41
     rough
    0.41
     descriptions
    0.41
     approximations
    0.41
     errands
    0.40
     comrade
    0.40
    츈
    0.40
    Activations Density 0.000%

    No Known Activations