© 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. 75302
    Prev
    Next
    INDEX
    Explanations

    will or might predictions

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

    compound modifiers and foreign words

    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
     T
    0.50
     Wh
    0.50
     rond
    0.49
     n
    0.49
     h
    0.47
     Wel
    0.47
     wh
    0.47
    高志森
    0.46
     J
    0.45
    مر
    0.45
    POSITIVE LOGITS
     disturbs
    0.54
     отсутствии
    0.53
     checkboxes
    0.52
     ಅನ್ನ
    0.50
     ঃ
    0.49
    сную
    0.49
    чную
    0.49
    omé
    0.48
    də
    0.48
    osiery
    0.48
    Activations Density 0.000%

    No Known Activations