© 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. 88088
    Prev
    Next
    INDEX
    Explanations

    guitar and bass strings

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

    job description

    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
    。
    0.55
    다
    0.53
    s
    0.51
    u
    0.51
    서
    0.50
    y
    0.50
    am
    0.50
    у
    0.49
    af
    0.49
    my
    0.49
    POSITIVE LOGITS
     wreaths
    0.61
     wreath
    0.61
     exquisite
    0.54
     hamm
    0.52
     hammock
    0.51
     yǐ
    0.51
     garland
    0.50
     ladr
    0.50
     garlands
    0.50
     ofer
    0.50
    Activations Density 0.001%

    No Known Activations