© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136048
    Prev
    Next
    INDEX
    Explanations

    confidentiality and frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ah
    0.52
    without
    0.52
    È
    0.50
    ils
    0.47
    on
    0.46
    Turkey
    0.46
    rate
    0.45
    as
    0.45
    en
    0.45
    let
    0.44
    POSITIVE LOGITS
     낮
    0.51
     spécialistes
    0.47
     pessim
    0.47
     qualità
    0.46
     veden
    0.46
     감소
    0.46
     faithfulness
    0.45
     baseline
    0.45
     kvalitet
    0.44
     специалисты
    0.44
    Activations Density 0.003%

    No Known Activations