© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95216
    Prev
    Next
    INDEX
    Explanations

    whether, because, ones, use, it, by, we, which

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

    as requested

    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
     {
    0.43
    ↵↵↵↵↵↵↵
    0.41
    ковая
    0.41
     उपरोक्त
    0.41
    Punjab
    0.41
    boro
    0.40
    omethane
    0.40
     Pharmacy
    0.40
    /
    0.40
     staat
    0.40
    POSITIVE LOGITS
     ඔහුගේ
    0.62
    𝔬
    0.51
     njegov
    0.47
     njegova
    0.42
     اسپ
    0.41
    𝐃
    0.41
    他在
    0.41
     त्याचे
    0.40
    ॉयड
    0.40
     клуб
    0.40
    Activations Density 0.001%

    No Known Activations