© 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. 50492
    Prev
    Next
    INDEX
    Explanations

    dreaming about things

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

    however, I can offer

    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
    nj
    0.53
    s
    0.51
    umber
    0.48
    dons
    0.48
    ną
    0.48
    mtext
    0.47
    nio
    0.47
    ider
    0.47
    ideo
    0.47
    omed
    0.46
    POSITIVE LOGITS
     victoire
    0.49
    劑
    0.48
     agir
    0.47
     conectados
    0.47
    他是
    0.46
    เชื่อม
    0.46
     شكله
    0.46
    原子
    0.45
    於是
    0.45
    تهي
    0.45
    Activations Density 0.000%

    No Known Activations