© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25331
    Prev
    Next
    INDEX
    Explanations

    current date and month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ã
    0.50
    ши
    0.47
    OFF
    0.43
     เปิด
    0.43
    iszt
    0.42
    ЕНИ
    0.42
    яви
    0.40
    Chiều
    0.40
    ameen
    0.40
    ï
    0.40
    POSITIVE LOGITS
     hyp
    0.48
     potassium
    0.44
     subjekt
    0.44
     lombok
    0.42
     removable
    0.40
     mv
    0.40
     sadece
    0.40
     fint
    0.40
     تړل
    0.40
     hydrogen
    0.39
    Activations Density 0.003%

    No Known Activations