© 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. 62423
    Prev
    Next
    INDEX
    Explanations

    word origin or definition

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

    definitions and associated words

    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
    atthakath
    0.53
     герцо
    0.52
     ब्रिटेन
    0.49
    σου
    0.49
     ব্রিটেনের
    0.47
    閬
    0.47
     अंग्रेज
    0.46
    फील्ड
    0.46
    ἅ
    0.46
     був
    0.46
    POSITIVE LOGITS
    3
    0.47
    2
    0.45
     juga
    0.44
    番
    0.43
     بهم
    0.43
     trauma
    0.43
     bump
    0.43
     움직
    0.43
     de
    0.42
     이동
    0.42
    Activations Density 0.012%

    No Known Activations