© 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. 155491
    Prev
    Next
    INDEX
    Explanations

    emergency landingBoard backsis almost

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

    classical physics limitations explained

    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
    章
    0.50
    ţi
    0.48
    ız
    0.46
    ümer
    0.46
     Benutzer
    0.45
    Mannschaft
    0.45
    る
    0.45
    શિ
    0.44
    zah
    0.44
    anı
    0.43
    POSITIVE LOGITS
     fake
    0.49
     cabbage
    0.48
     fossils
    0.47
     अमेठी
    0.47
     wine
    0.46
     copolymers
    0.46
     커피
    0.46
     happiness
    0.44
     goldfish
    0.44
     known
    0.44
    Activations Density 0.000%

    No Known Activations