© 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. 70145
    Prev
    Next
    INDEX
    Explanations

    in vitro, difficile, Wonderland, tank, coli

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

    software libraries and code elements

    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
     Chica
    0.41
    ♊
    0.40
     Hoodie
    0.39
    iney
    0.39
    ঘ্রই
    0.38
    aterData
    0.38
     Shade
    0.37
    ate
    0.37
    setWindowTitle
    0.36
     Aquatic
    0.36
    POSITIVE LOGITS
    󰡔
    0.53
     に対
    0.48
     に対して
    0.48
    に対する
    0.46
    observations
    0.44
     terhadap
    0.43
    говори
    0.43
     的
    0.42
     ，
    0.42
    づくり
    0.41
    Activations Density 0.176%

    No Known Activations