© 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. 86328
    Prev
    Next
    INDEX
    Explanations

    measurement words, numbers, or foreign words

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

    UN Observer States, funding

    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
    றிவு
    0.47
     الده
    0.47
     علماء
    0.44
    imidazol
    0.44
     ممال
    0.42
    halogen
    0.42
    隰
    0.42
    嗟
    0.41
     Prüfung
    0.41
     исправ
    0.41
    POSITIVE LOGITS
     staffing
    0.52
    2
    0.51
    ্ড
    0.51
    птова
    0.50
     operasi
    0.49
     stora
    0.49
     kass
    0.48
     operation
    0.48
     operating
    0.48
    erit
    0.48
    Activations Density 0.000%

    No Known Activations