© 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. 162354
    Prev
    Next
    INDEX
    Explanations

    racing pigeon, Regular Rolls, her photograph

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

    standard deviation or problem

    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
    লা
    0.42
     झालेल्या
    0.42
     XXV
    0.42
    чил
    0.41
    ).$$
    0.41
     Nations
    0.39
    эл
    0.39
     Василий
    0.39
    หย
    0.39
    楂
    0.39
    POSITIVE LOGITS
     Sicher
    0.49
    zov
    0.49
    虻
    0.46
    zug
    0.46
     മാത്ര
    0.45
     Krä
    0.43
    odont
    0.43
     மட்டுமே
    0.43
    inception
    0.43
     herramient
    0.43
    Activations Density 0.000%

    No Known Activations