© 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. 223756
    Prev
    Next
    INDEX
    Explanations

    prior to `a` or `an`

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

    metadata protection, collection, minimization

    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
     getBitmap
    0.51
     gốc
    0.51
     dropping
    0.50
     }}">
    0.50
    ಿಯೇ
    0.49
     któ
    0.49
     pozdě
    0.48
     ಸುದ್ದ
    0.47
     외
    0.46
     topRight
    0.45
    POSITIVE LOGITS
    Res
    0.50
    Vac
    0.50
    Uma
    0.50
    ла
    0.49
    一名
    0.49
    ท
    0.48
    SAL
    0.48
     syll
    0.47
    Vi
    0.46
    Esper
    0.46
    Activations Density 0.000%

    No Known Activations