© 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. 106169
    Prev
    Next
    INDEX
    Explanations

    service and role

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

    demonstrate how

    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
     stash
    0.46
    portál
    0.45
     सैकड़ों
    0.45
     거기
    0.45
    Gmail
    0.44
     ವಿವರ
    0.44
    murder
    0.44
    昔
    0.42
    がたくさん
    0.42
     長
    0.42
    POSITIVE LOGITS
     Aesthetic
    0.47
     Aesthetics
    0.46
     Turbine
    0.46
     Educ
    0.45
     potencial
    0.45
     potential
    0.45
     Soil
    0.44
     Expression
    0.43
     Alps
    0.43
     Ecole
    0.43
    Activations Density 0.000%

    No Known Activations