© 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. 95043
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and connectors

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

    qualifier followed by descriptor

    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
     Ferté
    0.46
     viewing
    0.46
    ừng
    0.46
     Tuy
    0.45
     glassy
    0.45
    ተ
    0.45
    δώ
    0.45
     treasured
    0.44
     সেই
    0.44
     forbidden
    0.43
    POSITIVE LOGITS
     требуют
    0.58
     attham
    0.47
     аспек
    0.46
     manca
    0.46
    ⏭
    0.45
     چلے
    0.45
    RAND
    0.44
    Lim
    0.44
     сезо
    0.44
     участок
    0.44
    Activations Density 0.001%

    No Known Activations