© 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. 113247
    Prev
    Next
    INDEX
    Explanations

    headline or review excerpts

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

    technical computing terms

    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
    今の
    0.44
    appliquer
    0.43
     अनुश
    0.42
    쪽에
    0.41
    ortex
    0.40
    現状
    0.40
    ύ
    0.40
    Answers
    0.40
    Describe
    0.40
    ای
    0.39
    POSITIVE LOGITS
     headline
    0.46
     Headlines
    0.43
    headlines
    0.43
     headlines
    0.42
    ]-->
    0.40
     हुन
    0.39
     Итали
    0.38
     Munch
    0.38
     нако
    0.38
    merz
    0.38
    Activations Density 0.001%

    No Known Activations