© 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. 202925
    Prev
    Next
    INDEX
    Explanations

    territory and president names

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

    LEGO blocks, devastating, impossibility, tied

    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
    트를
    0.53
    Kelas
    0.50
    冫
    0.49
    を受
    0.48
    چہ
    0.48
    טל
    0.47
    फो
    0.47
    STANDARD
    0.47
    婉
    0.47
    棻
    0.47
    POSITIVE LOGITS
     那麼
    0.50
     ហើយ
    0.50
     \
    0.49
     district
    0.49
     ridiculously
    0.49
     dangerous
    0.48
     cambiado
    0.48
     we
    0.48
     pagina
    0.47
     बोलते
    0.47
    Activations Density 0.000%

    No Known Activations