© 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. 64175
    Prev
    Next
    INDEX
    Explanations

    food ingredients and mixtures

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

    natural description or factual statement

    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
    ח
    0.53
    ק
    0.52
    ра
    0.47
    깬
    0.47
    אס
    0.47
    爭
    0.46
    рок
    0.45
    ורי
    0.45
    嫻
    0.45
    לה
    0.44
    POSITIVE LOGITS
    သောအ
    0.45
     healthful
    0.44
     Archbishop
    0.42
     Wesleyan
    0.41
     स्वाभाविक
    0.41
    cityName
    0.41
     Puma
    0.40
     Female
    0.39
     Plex
    0.39
     female
    0.39
    Activations Density 0.000%

    No Known Activations