© 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. 94673
    Prev
    Next
    INDEX
    Explanations

    time or additional details

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

    art nouveau, charging, stack, ultimately

    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
     Trevor
    0.47
    桠
    0.47
     Änderung
    0.46
    ڵی
    0.46
    eluarkan
    0.46
     funktionieren
    0.45
    狼
    0.45
     Aufgabe
    0.45
     গ্রুপের
    0.45
    跶
    0.45
    POSITIVE LOGITS
    сти
    0.44
    añas
    0.42
    يا
    0.42
    Prefab
    0.42
    ud
    0.41
     peč
    0.41
     clip
    0.41
    zas
    0.40
    clip
    0.40
    to
    0.39
    Activations Density 0.000%

    No Known Activations