© 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. 195012
    Prev
    Next
    INDEX
    Explanations

    unnecessary offence

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

    proceed until

    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
     quelcon
    0.44
    ︵
    0.42
     intérêts
    0.41
    蛋白質
    0.41
    峨
    0.41
    ᕕ
    0.41
    棻
    0.41
     núcleo
    0.41
    情绪
    0.41
     couvertures
    0.41
    POSITIVE LOGITS
    ান্ত্রিক
    0.55
     ಅನ
    0.50
    bagian
    0.48
     describ
    0.47
     unlawful
    0.46
     unm
    0.45
    pym
    0.44
    =(
    0.42
    =-\
    0.42
    pod
    0.42
    Activations Density 0.001%

    No Known Activations