© 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. 70219
    Prev
    Next
    INDEX
    Explanations

    danger points and pros

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

    environmental, financial, or programming tasks

    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
    ཌ
    0.50
     deviennent
    0.49
     monotonic
    0.47
     racionais
    0.42
     monomial
    0.42
     supernovae
    0.42
     dgn
    0.41
     multiplicative
    0.41
     glycogen
    0.40
     monotone
    0.40
    POSITIVE LOGITS
    👉
    0.48
    eka
    0.43
    ‘
    0.42
    le
    0.42
    attia
    0.41
    atti
    0.41
    nydd
    0.41
    te
    0.40
    aga
    0.40
     özelliği
    0.39
    Activations Density 0.037%

    No Known Activations