© 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. 13261
    Prev
    Next
    INDEX
    Explanations

    has an article or been

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

    describing characteristics or features

    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
     deras
    0.50
     jeweil
    0.47
     njihov
    0.47
     njima
    0.47
    堬
    0.47
     группе
    0.46
     THEIR
    0.46
     către
    0.45
     jeweiligen
    0.45
     ഇത്തരം
    0.45
    POSITIVE LOGITS
     been
    0.89
     a
    0.88
     an
    0.81
     seven
    0.76
     two
    0.74
    been
    0.73
    two
    0.71
     three
    0.70
     six
    0.70
     no
    0.69
    Activations Density 0.222%

    No Known Activations