© 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. 62563
    Prev
    Next
    INDEX
    Explanations

    moved westward

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

    multilingual text components

    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
    cture
    0.50
    xe
    0.49
    u
    0.49
    let
    0.48
    attiv
    0.46
    kin
    0.46
    Cet
    0.45
    vel
    0.44
     filesystem
    0.44
    ican
    0.43
    POSITIVE LOGITS
     綿
    0.52
     அமைச்ச
    0.51
     リン
    0.51
     どれ
    0.51
     автоматтары
    0.49
    یرے
    0.48
     見
    0.48
    数は
    0.48
     दिखता
    0.48
     kabupaten
    0.48
    Activations Density 0.000%

    No Known Activations