© 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. 112151
    Prev
    Next
    INDEX
    Explanations

    any fees

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

    crucial historical medical information

    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
     午前
    0.55
     Konya
    0.54
     ショルダー
    0.52
     胸
    0.51
     bora
    0.51
     ボ
    0.50
     pretentious
    0.50
     トート
    0.48
     Hola
    0.47
     ၀
    0.47
    POSITIVE LOGITS
    ouble
    0.54
    of
    0.53
    ells
    0.53
    ope
    0.52
    aque
    0.49
    ivil
    0.47
    azzo
    0.47
    Ě
    0.47
    aje
    0.47
    op
    0.46
    Activations Density 0.001%

    No Known Activations