© 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. 26675
    Prev
    Next
    INDEX
    Explanations

    projects and concepts

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

    listing information or categories

    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
    ในการ
    0.40
    这部
    0.40
    ாமல்
    0.39
     plötzlich
    0.38
    ồ
    0.36
    這個
    0.35
    return
    0.35
    ล
    0.35
    Ã
    0.34
    这个
    0.34
    POSITIVE LOGITS
     oraz
    0.57
    。
    0.53
     thereof
    0.52
    ။
    0.51
     以及
    0.49
     sekä
    0.47
    以及
    0.46
     તથા
    0.46
     તેમજ
    0.45
     그리고
    0.44
    Activations Density 0.129%

    No Known Activations