© 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. 54110
    Prev
    Next
    INDEX
    Explanations

    wallplate, intake, motocross, sacramental

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

    formal assumptions

    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
     fif
    0.59
     ν
    0.54
     Fif
    0.53
     Luxemb
    0.53
     statut
    0.52
     Nations
    0.50
    施行
    0.49
     Popul
    0.49
     Fig
    0.49
     Mathe
    0.49
    POSITIVE LOGITS
    ts
    0.51
    tis
    0.51
    к
    0.48
    traffic
    0.47
    tc
    0.46
     ब्लॉक
    0.46
    parsedBlock
    0.46
    क्स
    0.45
     загру
    0.45
    ta
    0.44
    Activations Density 0.000%

    No Known Activations