© 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. 80991
    Prev
    Next
    INDEX
    Explanations

    specific words preceding context

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

    physical phenomena and non-English words

    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
    thirty
    0.50
     Einf
    0.47
     কথোপ
    0.46
     Traverse
    0.45
     قبض
    0.44
     ملی
    0.44
     Durchmesser
    0.44
    蜊
    0.44
    compliance
    0.43
     Quarantine
    0.43
    POSITIVE LOGITS
    עות
    0.54
    НГ
    0.51
    на
    0.51
    ди
    0.49
    ги
    0.49
    чета
    0.47
    כה
    0.47
    од
    0.46
    гів
    0.46
    ана
    0.46
    Activations Density 0.001%

    No Known Activations