© 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. 36055
    Prev
    Next
    INDEX
    Explanations

    Letter Signed

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

    choices, selected, old

    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
     تُ
    0.51
    esh
    0.46
     تاع
    0.45
     cirk
    0.44
     smartest
    0.44
    ('=
    0.43
    kých
    0.43
     Loom
    0.43
     Spinal
    0.43
     வணிக
    0.43
    POSITIVE LOGITS
    ра
    0.51
     aujourd
    0.50
    "?>
    0.48
    リ
    0.46
    Prote
    0.46
    Papers
    0.46
     emol
    0.46
    SCIENCE
    0.45
    たん
    0.45
    엷
    0.44
    Activations Density 0.000%

    No Known Activations