© 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. 161570
    Prev
    Next
    INDEX
    Explanations

    sales funnels. antibodies. ladders anyhow. dancing. event, targeted market

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

    Walder Frey

    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
    흄
    0.49
     scripted
    0.46
    lawful
    0.46
    documented
    0.45
    ماس
    0.44
    ہنی
    0.44
    defined
    0.43
    푹
    0.42
    claimed
    0.41
    loin
    0.41
    POSITIVE LOGITS
    VD
    0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.52
     romances
    0.51
     บาง
    0.50
     เรื่อง
    0.49
     थे
    0.49
    О
    0.49
    aña
    0.48
     Katar
    0.48
     histone
    0.48
    Activations Density 0.000%

    No Known Activations