© 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. 86208
    Prev
    Next
    INDEX
    Explanations

    obviamente, obviously, indeed

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

    list of items

    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
     πρώτη
    0.43
     ನೀರಿನ
    0.43
    ଥ
    0.41
     женщина
    0.41
    !”.
    0.41
     ನೀ
    0.40
    .”.
    0.40
    ᱝ
    0.40
    ίων
    0.40
    beginning
    0.39
    POSITIVE LOGITS
     obviamente
    0.54
     ovviamente
    0.48
     hyperparameters
    0.48
    datei
    0.48
     obviously
    0.47
     memang
    0.46
    されており
    0.46
    ですし
    0.46
    entuan
    0.45
     sedang
    0.44
    Activations Density 0.000%

    No Known Activations