© 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. 45321
    Prev
    Next
    INDEX
    Explanations

    actual is telling

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

    largest market

    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
    Об
    0.52
    ão
    0.51
     पुन्हा
    0.51
    Ф
    0.50
    Une
    0.50
     পরই
    0.50
    isocyanate
    0.49
    Tunes
    0.49
    X
    0.49
    hypothesis
    0.48
    POSITIVE LOGITS
     memoria
    0.45
     mbi
    0.45
     Boley
    0.42
    赎
    0.42
     memo
    0.41
     temperament
    0.41
    有好
    0.41
     Goddard
    0.40
    缦
    0.40
     jQuery
    0.40
    Activations Density 0.000%

    No Known Activations