© 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. 175747
    Prev
    Next
    INDEX
    Explanations

    window-chutes or loft space

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

    detection of

    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
    ঙ্গ
    0.54
    ן
    0.49
    、“
    0.47
     zabez
    0.47
    ാ
    0.46
     İz
    0.46
    ঙ
    0.46
    、「
    0.45
     Innen
    0.45
     Erfol
    0.45
    POSITIVE LOGITS
     دیتے
    0.46
     ہتھیار
    0.46
    кистон
    0.46
    fit
    0.45
    quin
    0.43
    illon
    0.43
    rakash
    0.43
    economics
    0.42
    restassured
    0.42
    固定
    0.41
    Activations Density 0.000%

    No Known Activations