© 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. 43608
    Prev
    Next
    INDEX
    Explanations

    as well

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

    explaining Gemma or states

    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
     đô
    0.51
    向けの
    0.48
    ATE
    0.48
     đất
    0.47
     শহর
    0.46
    ર્થ
    0.46
    ﾝ
    0.46
     chủ
    0.46
     bạn
    0.46
    者
    0.45
    POSITIVE LOGITS
     permutations
    0.53
     растений
    0.48
     marvellous
    0.48
     complicated
    0.48
     собственно
    0.46
    Вот
    0.45
     elucidation
    0.45
     rattling
    0.45
    段时间
    0.44
     volition
    0.44
    Activations Density 0.000%

    No Known Activations