© 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. 21273
    Prev
    Next
    INDEX
    Explanations

    ranging from to

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

    ranging from

    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
     shrinking
    0.57
    。
    0.50
    ។
    0.50
    nil
    0.49
    setzung
    0.48
     its
    0.47
     resonance
    0.47
     multiplication
    0.46
    ों
    0.46
     ற
    0.46
    POSITIVE LOGITS
     från
    0.70
     từ
    0.67
     ranging
    0.61
     από
    0.57
    จาก
    0.57
     varía
    0.55
     بین
    0.54
     dari
    0.54
     između
    0.54
     두고
    0.54
    Activations Density 0.007%

    No Known Activations