© 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. 33307
    Prev
    Next
    INDEX
    Explanations

    content/description of features

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

    levels of detail

    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
    പ്പെടുത്ത
    0.48
     měst
    0.47
     Chỉ
    0.47
     stadiums
    0.46
     parceria
    0.45
     oraș
    0.45
    ři
    0.44
    嶽
    0.44
     pono
    0.44
     Genève
    0.43
    POSITIVE LOGITS
    \
    0.54
     content
    0.48
    亮度
    0.48
     contento
    0.47
     questioned
    0.46
    例子
    0.46
     complicated
    0.45
     perplexed
    0.45
     hesitated
    0.44
    Presenter
    0.44
    Activations Density 0.000%

    No Known Activations