© 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. 216538
    Prev
    Next
    INDEX
    Explanations

    phrase completions

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

    description of attributes or actions

    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
    ли
    0.50
    莖
    0.49
     início
    0.48
    控制
    0.46
    曏
    0.46
     ಮೇ
    0.45
    歷
    0.45
    饑
    0.44
     Бан
    0.44
    }^\
    0.44
    POSITIVE LOGITS
     unprofessional
    0.52
     treacherous
    0.48
     doable
    0.45
    uddersfield
    0.45
     reinsurance
    0.45
     fera
    0.44
     surfboard
    0.43
     connector
    0.43
     gew
    0.43
     reseller
    0.42
    Activations Density 0.001%

    No Known Activations