© 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. 177449
    Prev
    Next
    INDEX
    Explanations

    you may

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

    intensive, demanding, skills

    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
     হইয়৷
    0.57
     ASPECTS
    0.54
     канторы
    0.51
     REGIUNI
    0.48
     сега
    0.48
    lsen
    0.48
     қи
    0.48
     barrios
    0.47
     soms
    0.47
    rath
    0.47
    POSITIVE LOGITS
    add
    0.50
    after
    0.46
    n
    0.44
    label
    0.44
    Et
    0.44
    ንድ
    0.43
    int
    0.43
    reversible
    0.43
    itimate
    0.42
    alım
    0.42
    Activations Density 0.000%

    No Known Activations