© 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. 164221
    Prev
    Next
    INDEX
    Explanations

    institutional and technical terms

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

    pluralization and categorization

    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
    ぃ
    0.50
    くと
    0.49
    みな
    0.49
    熱
    0.48
    獲得
    0.48
     ультра
    0.48
     batu
    0.47
    می
    0.47
    ovaný
    0.47
    ↵
    0.46
    POSITIVE LOGITS
    校长
    0.45
     אחרי
    0.45
    ücher
    0.44
    ensin
    0.44
     기관
    0.44
     прио
    0.43
     गुर्जर
    0.43
    upuncture
    0.42
    abinieri
    0.42
    exual
    0.42
    Activations Density 0.001%

    No Known Activations