© 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. 116881
    Prev
    Next
    INDEX
    Explanations

    describing specific things

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

    asterisk replacement or bullet points

    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
    ed
    0.54
    f
    0.50
     Callable
    0.50
    ing
    0.47
    ontrol
    0.46
     Afterward
    0.45
     Supervision
    0.45
    ohol
    0.44
    uk
    0.44
    osen
    0.44
    POSITIVE LOGITS
    Ｂ
    0.50
     karyawan
    0.46
    वीपी
    0.46
    verständlich
    0.45
    咽
    0.45
    吞
    0.44
     구축
    0.44
    Ⲕ
    0.44
     हृदया
    0.43
    舞
    0.43
    Activations Density 0.001%

    No Known Activations