© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15173
    Prev
    Next
    INDEX
    Explanations

    food categories and nutrition

    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
     예상
    0.49
    訃
    0.48
    డీపీ
    0.48
     неред
    0.47
     футболка
    0.45
     информации
    0.45
     автомобиль
    0.44
    ພາບ
    0.44
     بخاری
    0.44
    ቪ
    0.44
    POSITIVE LOGITS
    euro
    0.44
     dungeons
    0.43
     manic
    0.42
    each
    0.41
     fingers
    0.41
     application
    0.41
    oue
    0.41
     yields
    0.41
     unfolds
    0.41
     successivo
    0.40
    Activations Density 0.010%

    No Known Activations