© 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. 246154
    Prev
    Next
    INDEX
    Explanations

    legal or identifying terms

    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
     لدينا
    0.51
     नवंबर
    0.50
    rugula
    0.48
     売
    0.46
    securityMarks
    0.44
     ၀
    0.44
    Benzoimidazole
    0.43
     Depreciation
    0.42
    ventions
    0.41
     Carpath
    0.41
    POSITIVE LOGITS
    แต่
    0.45
     agar
    0.44
     sedang
    0.44
     mutta
    0.43
     undisputed
    0.42
     woes
    0.42
     visto
    0.42
     adik
    0.42
    蛮
    0.42
    มาก
    0.41
    Activations Density 0.002%

    No Known Activations