© 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. 238225
    Prev
    Next
    INDEX
    Explanations

    zones, season, ventilation, nginx, its

    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
    ены
    0.50
     औपचारिक
    0.45
    anlı
    0.45
    inating
    0.44
     تهران
    0.44
     شهری
    0.44
    廾
    0.43
     दर्जा
    0.43
    inence
    0.43
    本质
    0.42
    POSITIVE LOGITS
    ᚄ
    0.48
    皇帝
    0.47
     ouvido
    0.46
    꿋
    0.46
     appareil
    0.46
     jogador
    0.45
     prefeito
    0.45
    OI
    0.44
    šť
    0.44
     zase
    0.44
    Activations Density 0.000%

    No Known Activations