© 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. 128556
    Prev
    Next
    INDEX
    Explanations

    malware, economy, arrested, outbreak, dance

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

    wide range

    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
    腸
    0.54
    ᱢ
    0.49
     pequeñas
    0.49
     privados
    0.49
     উদ্ভিদ
    0.48
     clínicos
    0.46
     pequeños
    0.46
     세포
    0.45
    だな
    0.44
    疹
    0.44
    POSITIVE LOGITS
    ad
    0.63
    an
    0.63
    pe
    0.61
     an
    0.60
    ig
    0.58
    ib
    0.57
    en
    0.56
    al
    0.56
    ar
    0.56
    es
    0.54
    Activations Density 0.000%

    No Known Activations