© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    determining or calculating something

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

    want to find

    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
    벤
    0.41
     Everybody
    0.40
     Carnival
    0.39
    entimes
    0.38
     water
    0.36
     Never
    0.36
     plen
    0.36
    水
    0.36
     Everyone
    0.35
    pk
    0.35
    POSITIVE LOGITS
     понять
    0.65
     demostrar
    0.64
     apakah
    0.61
    找出
    0.55
     capire
    0.55
     démontrer
    0.55
     determinar
    0.54
    どのように
    0.53
     কতটা
    0.52
     எவ்வாறு
    0.52
    Activations Density 0.001%

    No Known Activations