© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57426
    Prev
    Next
    INDEX
    Explanations

    describing change, systems, goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しますが
    0.37
    いますが
    0.33
    しましたが
    0.33
     लेकिन
    0.32
     But
    0.31
    と思いますが
    0.31
    ;
    0.31
     buts
    0.30
     pero
    0.30
     ولكن
    0.30
    POSITIVE LOGITS
     ਉਨ੍ਹਾਂ
    0.37
     ג
    0.35
    ִ
    0.35
    입니다
    0.34
     ತಮ್ಮ
    0.34
     ፡፡
    0.32
    이다
    0.32
     입니다
    0.32
     ”.
    0.31
     של
    0.31
    Activations Density 0.043%

    No Known Activations