© 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. 49735
    Prev
    Next
    INDEX
    Explanations

    savoury selection

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

    speed and scheduling

    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
    珵
    0.68
     עבור
    0.57
    Consulta
    0.54
    谘
    0.53
    InCM
    0.53
    กับ
    0.52
    만큼
    0.52
    Emple
    0.51
    에
    0.51
    也是
    0.50
    POSITIVE LOGITS
    ’
    0.60
     l
    0.58
    ru
    0.57
     '
    0.54
    _{
    0.53
     Fas
    0.53
     Britain
    0.52
     "
    0.52
    '
    0.52
     d
    0.50
    Activations Density 0.001%

    No Known Activations