© 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. 25856
    Prev
    Next
    INDEX
    Explanations

    dipped below, referring to

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

    refine understanding

    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
    4
    0.52
    5
    0.50
    9
    0.47
    6
    0.46
    but
    0.46
    7
    0.46
    Queen
    0.45
    0
    0.44
    ٦
    0.44
    說是
    0.43
    POSITIVE LOGITS
     dwRes
    0.52
     lluvias
    0.45
     orgull
    0.44
     സൃഷ്ട
    0.43
     codebase
    0.43
     создания
    0.42
     vzděl
    0.41
     educativa
    0.41
     koos
    0.40
     створи
    0.39
    Activations Density 0.000%

    No Known Activations