© 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. 67557
    Prev
    Next
    INDEX
    Explanations

    our services or operating expenses

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

    programmed language examples

    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
    t
    0.67
    las
    0.55
    s
    0.54
    es
    0.52
    lo
    0.52
    clas
    0.50
    la
    0.50
    ral
    0.50
    net
    0.50
    ces
    0.49
    POSITIVE LOGITS
     仕事
    0.69
     書い
    0.59
     ឬ
    0.59
     高級
    0.59
     ಅಥವಾ
    0.56
     හෝ
    0.55
    ₕ
    0.55
     開
    0.55
     おはよう
    0.54
    หรือ
    0.54
    Activations Density 0.000%

    No Known Activations