© 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. 88888
    Prev
    Next
    INDEX
    Explanations

    relationship between months and events

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

    successor function and PageRank

    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
    СК
    0.45
     فِي
    0.45
     ت
    0.45
     للس
    0.45
     молод
    0.43
     Павел
    0.43
    iooni
    0.43
     XXI
    0.42
    ުރު
    0.42
    VI
    0.42
    POSITIVE LOGITS
    puce
    0.42
    Fused
    0.41
     unlabeled
    0.41
    ws
    0.41
     বিদেশি
    0.41
    /");
    0.40
     आदत
    0.40
     ursprüng
    0.39
     habitudes
    0.39
     suppuration
    0.39
    Activations Density 0.000%

    No Known Activations