© 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. 237546
    Prev
    Next
    INDEX
    Explanations

    headspace

    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
     acque
    0.40
    ムー
    0.40
     جات
    0.40
    ورية
    0.39
    制的
    0.38
     ур
    0.38
     אחת
    0.38
     φ
    0.38
     inclusive
    0.38
     daba
    0.38
    POSITIVE LOGITS
    द्धाल
    0.49
     verir
    0.49
    verläss
    0.48
     Szent
    0.48
     Benutz
    0.47
    മല
    0.46
    wens
    0.46
    क्सीडेंट
    0.45
     Standards
    0.45
     कंपनियों
    0.45
    Activations Density 0.000%

    No Known Activations