© 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. 64085
    Prev
    Next
    INDEX
    Explanations

    specific items and their context

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

    descriptions of variance, responsibility, or cancer

    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
     demostrar
    0.46
     geografia
    0.45
     fainting
    0.44
     prolet
    0.43
    Боль
    0.42
     ataques
    0.41
    leton
    0.41
    冉
    0.41
    ﮐ
    0.40
    嶷
    0.40
    POSITIVE LOGITS
    日まで
    0.52
     ponctu
    0.50
    的总
    0.50
    ielle
    0.48
     назем
    0.47
     أرض
    0.45
     сус
    0.45
     канализа
    0.44
     Throughout
    0.44
    ęć
    0.44
    Activations Density 0.000%

    No Known Activations