© 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. 135135
    Prev
    Next
    INDEX
    Explanations

    selling it

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

    violence and production

    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
    ל
    0.52
    ्टी
    0.46
     ক্যাল
    0.45
    bets
    0.44
    賜
    0.43
    anz
    0.43
    ält
    0.43
    ದ
    0.43
    閲
    0.42
     আহমে
    0.42
    POSITIVE LOGITS
     violencia
    0.53
     idle
    0.51
     produces
    0.50
    ujourd
    0.48
     transg
    0.47
     qualquer
    0.46
     realizes
    0.46
     público
    0.46
     breathes
    0.46
     producido
    0.46
    Activations Density 0.000%

    No Known Activations