© 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. 134815
    Prev
    Next
    INDEX
    Explanations

    categories and classifications

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

    longing and dialogue

    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
    type
    0.45
    p
    0.44
     คุณ
    0.43
    quantitative
    0.43
    ation
    0.43
     conductance
    0.42
    uddho
    0.42
    预计
    0.41
    akkhanam
    0.41
     ۵
    0.41
    POSITIVE LOGITS
     personaje
    0.48
     minum
    0.47
     falt
    0.46
     responsabilità
    0.45
    掲載
    0.44
     sond
    0.44
    身份
    0.44
    她
    0.43
     inser
    0.43
     fix
    0.43
    Activations Density 0.001%

    No Known Activations