© 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. 120300
    Prev
    Next
    INDEX
    Explanations

    Apple iPhone

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

    speeds, still need, connects to

    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
    ବା
    0.48
     pagine
    0.46
     pendiente
    0.46
    শ্যক
    0.45
    䉼
    0.45
     ゆっくり
    0.44
    唒
    0.43
    శా
    0.42
     संधी
    0.42
     కేసులు
    0.42
    POSITIVE LOGITS
    برای
    0.50
    érature
    0.46
    uing
    0.45
    or
    0.42
    scrire
    0.42
    If
    0.39
     observation
    0.39
    íng
    0.39
    ivez
    0.39
     برای
    0.38
    Activations Density 0.002%

    No Known Activations