© 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. 28840
    Prev
    Next
    INDEX
    Explanations

    specific quantifier followed by noun

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

    text-to-text Transfer Transformer

    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
    ഡിയ
    0.57
    paint
    0.53
    visions
    0.50
    positioned
    0.50
    ਵੀ
    0.48
    Հ
    0.48
    ﮈ
    0.48
    capital
    0.48
    role
    0.47
    모
    0.47
    POSITIVE LOGITS
     cao
    0.46
     outperforms
    0.45
     decays
    0.44
     ejac
    0.44
     farmed
    0.43
     hao
    0.43
     sinc
    0.42
     från
    0.41
     eluted
    0.41
     своём
    0.41
    Activations Density 0.000%

    No Known Activations