© 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. 64516
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by details

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

    date and structured information

    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
     sizlere
    0.45
    ​​​​
    0.44
     পর্যা
    0.42
     timeframe
    0.40
     reverence
    0.40
     largos
    0.40
    $\,.
    0.40
    .​​
    0.40
    stylers
    0.39
    respons
    0.39
    POSITIVE LOGITS
    紧
    0.43
     imply
    0.42
     있으며
    0.41
     Tü
    0.41
     있고
    0.40
    示す
    0.40
     Tuz
    0.40
     نضيف
    0.40
    力和
    0.39
     번째
    0.38
    Activations Density 0.000%

    No Known Activations