© 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. 46037
    Prev
    Next
    INDEX
    Explanations

    ball mill

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

    look at clock or text

    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
    ש
    0.50
     Niagara
    0.44
    ミネ
    0.44
    CASCADE
    0.43
    COLLATION
    0.43
     Spir
    0.43
    INE
    0.42
    ശു
    0.41
    anima
    0.41
     Vinh
    0.41
    POSITIVE LOGITS
    悦
    0.46
    参数
    0.44
    parameter
    0.43
    发言
    0.43
    rho
    0.43
     tamaños
    0.42
    ұл
    0.42
    享
    0.42
     parameter
    0.41
    ርግ
    0.41
    Activations Density 0.000%

    No Known Activations