© 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. 219473
    Prev
    Next
    INDEX
    Explanations

    spending about

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

    Not perfectly round

    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
     unscathed
    0.54
     foresight
    0.52
    အနေ
    0.52
     انتہائی
    0.51
    䧺
    0.49
     ಒತ್ತ
    0.48
     grapple
    0.48
     സംഭ
    0.47
     teammates
    0.47
     aumentare
    0.47
    POSITIVE LOGITS
    Cake
    0.52
    Echo
    0.50
    Warner
    0.49
    LessThan
    0.47
    Eb
    0.46
    Newly
    0.46
    Foe
    0.46
    E
    0.45
    라고
    0.44
    ற்றும்
    0.44
    Activations Density 0.000%

    No Known Activations