© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    so followed by quantity/degree

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

    let's break down / here's

    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
    зяржа
    0.26
    というのは
    0.26
    творення
    0.26
    idespread
    0.25
     ত
    0.25
     பயன்படுகிறது
    0.24
    ferred
    0.24
    clerosis
    0.23
    ឬ
    0.23
     (§
    0.23
    POSITIVE LOGITS
     susah
    0.29
     setColor
    0.29
     sano
    0.26
     jsonify
    0.25
     yaptık
    0.25
     dakkh
    0.25
     addItem
    0.25
     jod
    0.25
     prive
    0.24
     наверное
    0.24
    Activations Density 0.139%

    No Known Activations