© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7769
    Prev
    Next
    INDEX
    Explanations

    nuts and almonds

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

    nuts and seeds

    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_53_width_65k_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
    滘
    0.54
    霓
    0.50
    Vectorizer
    0.45
    荥
    0.44
    Mario
    0.42
    戳
    0.42
     UIColor
    0.40
    昷
    0.40
    霧
    0.39
     Mario
    0.38
    POSITIVE LOGITS
     nuts
    2.56
     almonds
    2.34
     Nuts
    2.34
     peanuts
    2.27
    nuts
    2.20
     walnuts
    2.16
     hazelnuts
    2.13
     pecans
    1.97
     almond
    1.84
     nut
    1.80
    Activations Density 0.156%

    No Known Activations