© 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. 32389
    Prev
    Next
    INDEX
    Explanations

    providing helpful information

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

    expressing helpfulness or usefulness

    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
     বলেও
    0.43
     besuchte
    0.41
     ससु
    0.39
     συνεχ
    0.38
     کامی
    0.38
     प्रतिभाशाली
    0.37
    部
    0.37
     sob
    0.37
     शक्तिशाली
    0.37
    就會
    0.37
    POSITIVE LOGITS
     information
    0.52
     informatie
    0.49
     정보
    0.48
     informações
    0.47
     alguna
    0.46
     algum
    0.46
     ?
    0.46
     информации
    0.45
     somewhat
    0.45
    情報は
    0.44
    Activations Density 0.022%

    No Known Activations