© 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. 190722
    Prev
    Next
    INDEX
    Explanations

    users, voice, focus, among, off, base

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

    bookstore, people, intelligence, friend

    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
    iebel
    0.50
    াস্থ্য
    0.49
    ंपर्यंत
    0.48
    اداسی
    0.48
     (
    0.45
     સુધી
    0.44
    ிருந்தால்
    0.44
    தள
    0.44
    ulum
    0.43
    ņi
    0.43
    POSITIVE LOGITS
     BOAT
    0.46
     ORDIN
    0.46
    ই
    0.46
    ಿಸ್
    0.46
    ﯿ
    0.45
     WEIGHT
    0.45
     AUR
    0.44
    上半
    0.44
    是一
    0.44
     malign
    0.43
    Activations Density 0.000%

    No Known Activations