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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 895
    Prev
    Next
    INDEX
    Explanations

    eating or preparing hearts

    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_16_width_65k_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
    f
    0.73
    z
    0.52
     and
    0.50
    ;
    0.50
    í
    0.50
    se
    0.49
    _
    0.49
    p
    0.48
    ل
    0.46
    q
    0.44
    POSITIVE LOGITS
     ebben
    0.50
     Лон
    0.47
    0.46
    О
    0.46
     ৮
    0.46
     requisito
    0.46
     учитель
    0.43
     около
    0.43
     negativos
    0.43
     créée
    0.42
    Activations Density 3.681%

    No Known Activations