© 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. 27255
    Prev
    Next
    INDEX
    Explanations

    division and fractions

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

    mathematical formatting and notation

    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
    াৎ
    0.53
    اف
    0.51
    ዻ
    0.48
     új
    0.48
     сила
    0.48
    Registre
    0.48
    实话
    0.47
     sujets
    0.46
     돈
    0.45
     intérêts
    0.45
    POSITIVE LOGITS
    established
    0.57
     بنائیں
    0.54
     established
    0.47
     segmented
    0.45
    segmented
    0.45
    atau
    0.43
    employed
    0.43
    time
    0.42
    ache
    0.42
    hline
    0.41
    Activations Density 0.001%

    No Known Activations