© 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. 462
    Prev
    Next
    INDEX
    Explanations

    financial prices

    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
    ഷ്ട്ര
    0.46
    ակի
    0.43
    嚣
    0.43
     പ്രത്യ
    0.42
     kalor
    0.42
    ោម
    0.42
    maar
    0.41
     prende
    0.41
     kişilik
    0.41
    ruari
    0.40
    POSITIVE LOGITS
    /
    0.42
    訲
    0.42
    uted
    0.41
     কমপক্ষে
    0.40
     फ़
    0.39
     slept
    0.38
    metrics
    0.38
     Ү
    0.37
     ሂ
    0.37
     লিখিত
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.