© 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. 24919
    Prev
    Next
    INDEX
    Explanations

    defining specific terms

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

    refusal of explicit or harmful requests

    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
     Soleil
    0.44
     cạnh
    0.42
    ).'
    0.42
    यह
    0.41
    ты
    0.40
     संभावनाएं
    0.40
    thaus
    0.39
     این
    0.39
    وہ
    0.39
    เท่า
    0.38
    POSITIVE LOGITS
    と呼ばれる
    0.77
     খ্যা
    0.73
     எனப்படும்
    0.65
    と呼ば
    0.51
     अर्थात्
    0.48
    所谓的
    0.47
     aka
    0.44
     (=
    0.44
    ™
    0.44
     अर्थात
    0.44
    Activations Density 0.259%

    No Known Activations