© 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. 72055
    Prev
    Next
    INDEX
    Explanations

    Tom Bradley

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

    goals in games

    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
    اسية
    0.45
    encije
    0.44
     posisi
    0.43
    ០
    0.43
     konkur
    0.42
    اسة
    0.42
    maxn
    0.42
    äfte
    0.41
     않
    0.41
    مة
    0.41
    POSITIVE LOGITS
     residencial
    0.53
     Londra
    0.50
     parametrization
    0.47
     Londres
    0.44
     CHANGE
    0.44
    London
    0.44
     PHONE
    0.44
     onload
    0.44
    लीकरण
    0.44
    கரு
    0.43
    Activations Density 0.000%

    No Known Activations