© 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. 89006
    Prev
    Next
    INDEX
    Explanations

    statements of possibility or claim

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

    both sides

    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
    רים
    0.48
    ΟΥ
    0.47
    אים
    0.47
    சில்
    0.45
     rebut
    0.45
    ר
    0.45
    송
    0.45
    ЕН
    0.44
    AR
    0.44
    ни
    0.43
    POSITIVE LOGITS
     konzerv
    0.54
     _.
    0.52
     Dogs
    0.48
     Ami
    0.47
    ظمة
    0.47
     histoires
    0.47
     Parc
    0.46
    bev
    0.46
     Amar
    0.46
    रेडी
    0.46
    Activations Density 0.000%

    No Known Activations