© 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. 58481
    Prev
    Next
    INDEX
    Explanations

    expense, loss, contest

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

    however, but

    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
    ätzung
    0.54
    ҳи
    0.51
    4
    0.50
     ఫ్రె
    0.49
    ኋ
    0.48
    ää
    0.48
    ivia
    0.46
    贸
    0.46
    虾
    0.46
     Grèce
    0.45
    POSITIVE LOGITS
     hosts
    0.52
    م
    0.48
     temas
    0.43
     penerapan
    0.43
     institut
    0.43
     conversaciones
    0.43
     monot
    0.43
     myeloid
    0.43
    राण
    0.43
    BOUNDARY
    0.42
    Activations Density 0.000%

    No Known Activations