© 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. 79376
    Prev
    Next
    INDEX
    Explanations

    began welcoming, passionately delivered, become mainstream

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

    sarcastic and funny answers

    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
     RADIOACTIVE
    0.50
     આવે
    0.47
    स्तक
    0.46
    在哪
    0.46
     йөк
    0.46
    <unused79>
    0.46
     वोल्ट
    0.46
     सूचीबद्ध
    0.46
     નામ
    0.46
     bequeathed
    0.45
    POSITIVE LOGITS
    i
    0.67
    I
    0.55
    ovanie
    0.54
    ování
    0.52
    reff
    0.51
    real
    0.50
    <em>
    0.49
     gaw
    0.49
    Progress
    0.49
    Can
    0.48
    Activations Density 0.000%

    No Known Activations