© 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. 12547
    Prev
    Next
    INDEX
    Explanations

    who should be

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

    specific conditions or continuations

    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
    中所
    0.47
    で作
    0.46
    joner
    0.45
     initialize
    0.44
     էր
    0.44
    ATUS
    0.43
     Iter
    0.42
    絕
    0.42
    湁
    0.41
     origin
    0.40
    POSITIVE LOGITS
     aunque
    0.47
     modernisation
    0.47
    ))$,
    0.46
     पण
    0.45
    眉头
    0.45
    তবে
    0.44
    2
    0.44
     tendances
    0.44
    Football
    0.43
     আঁচ
    0.43
    Activations Density 0.000%

    No Known Activations