© 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. 91509
    Prev
    Next
    INDEX
    Explanations

    specific words preceding punctuation

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

    sex slaves

    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
     fühlen
    0.54
     wool
    0.44
     чувство
    0.43
      
    0.43
     anda
    0.43
    ől
    0.43
    getahuan
    0.42
     ö
    0.42
     fö
    0.41
     biscuits
    0.41
    POSITIVE LOGITS
    牰
    0.47
    लित
    0.46
     کوردستان
    0.45
    Venezuela
    0.44
     ประเทศ
    0.43
     FMT
    0.43
    timestamp
    0.43
     Sellers
    0.43
    thisTrack
    0.43
    τητας
    0.42
    Activations Density 0.001%

    No Known Activations