© 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. 101800
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, or sequences

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

    offers convenience, fostered, frequently, black box, ChatGPT, weights

    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
    n
    0.64
    a
    0.63
    i
    0.62
    ن
    0.60
    न
    0.56
    려
    0.55
    н
    0.52
    혼
    0.52
    ago
    0.52
    נ
    0.50
    POSITIVE LOGITS
     tý
    0.49
     provoked
    0.47
     விற்ப
    0.47
     disadvant
    0.46
     সের
    0.46
     cú
    0.45
     показ
    0.45
     wèi
    0.45
     UIC
    0.45
     disgr
    0.45
    Activations Density 0.000%

    No Known Activations