© 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. 181945
    Prev
    Next
    INDEX
    Explanations

    classification and gradual scaling

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

    fail then return

    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
    ве
    0.50
    πε
    0.50
     назем
    0.49
    пиа
    0.48
     ή
    0.47
    かなり
    0.47
    ви
    0.47
    ോ
    0.47
     horas
    0.46
     স্ক
    0.46
    POSITIVE LOGITS
     empir
    0.52
     fail
    0.48
     Cause
    0.48
     emper
    0.46
     ruling
    0.45
     surpl
    0.45
     discredit
    0.45
     bestät
    0.44
     Season
    0.44
     multiplic
    0.44
    Activations Density 0.001%

    No Known Activations