© 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. 144803
    Prev
    Next
    INDEX
    Explanations

    reporting speech and actions

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

    call this

    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
    ლ
    0.57
    زندگی
    0.55
    ذ
    0.51
    ਲ
    0.49
    ाम्
    0.48
    transfected
    0.48
    عمال
    0.48
    ز
    0.48
    ੁੰ
    0.47
    比亚
    0.47
    POSITIVE LOGITS
    ecal
    0.46
     приятно
    0.46
     squarely
    0.45
     direto
    0.45
     diretamente
    0.45
     Doctor
    0.45
     городского
    0.44
     Hospital
    0.44
     TextView
    0.44
     neatly
    0.43
    Activations Density 0.000%

    No Known Activations