© 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. 46670
    Prev
    Next
    INDEX
    Explanations

    kettle, snips, small, janome, 2 drawer, color, medela, washing

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

    past tense verbs and descriptions

    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
     рейтинг
    0.48
     Wehr
    0.46
     драмати
    0.45
    得意
    0.44
     တစ်
    0.43
    </strong>
    0.43
     édition
    0.43
     Luxurious
    0.43
     Eldorado
    0.43
     conspiring
    0.42
    POSITIVE LOGITS
    เพลง
    0.52
    ITED
    0.51
    จ
    0.48
    ขาด
    0.48
    날
    0.46
    ITAL
    0.46
    Введите
    0.46
    安裝
    0.46
    은
    0.46
    ायत
    0.46
    Activations Density 0.000%

    No Known Activations