© 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. 121870
    Prev
    Next
    INDEX
    Explanations

    permissions, online services, technical/medical terms

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

    gentle humor, attached to

    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
    E
    0.50
    S
    0.48
    brook
    0.47
    奏
    0.47
    pias
    0.46
    V
    0.46
    τ
    0.45
    datasource
    0.44
    至
    0.44
    dS
    0.44
    POSITIVE LOGITS
     내용
    0.52
     نگرانی
    0.51
     antiviral
    0.50
     emissivity
    0.49
     berbahaya
    0.48
     meditating
    0.48
     maravilh
    0.47
     chromatographic
    0.47
     رم
    0.46
     rapports
    0.46
    Activations Density 0.000%

    No Known Activations