© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    top notch

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

    top lists and rankings

    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
     өз
    0.40
    ãy
    0.39
     swallowed
    0.39
    appendText
    0.39
     अपेक्षाकृत
    0.38
    ूपी
    0.38
    ennen
    0.38
    ⎞
    0.37
    `).
    0.36
    adeh
    0.36
    POSITIVE LOGITS
    notch
    1.34
     notch
    1.20
     tier
    1.05
     Notch
    0.95
    ographically
    0.90
    স্থানীয়
    0.88
    flight
    0.81
    iary
    0.80
    ographies
    0.80
    ographical
    0.80
    Activations Density 0.096%

    No Known Activations