© 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. 181770
    Prev
    Next
    INDEX
    Explanations

    phrases with specific following words

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

    Eighty Percent, AI models

    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
    守
    0.47
    숱
    0.42
     reg
    0.42
    同志
    0.41
     bizi
    0.41
     galore
    0.41
    渠
    0.40
    當時
    0.40
    δε
    0.40
    чек
    0.39
    POSITIVE LOGITS
     Kindness
    0.54
    angor
    0.51
     پور
    0.50
     Rockets
    0.48
     নিন
    0.48
     Кор
    0.48
     तयारी
    0.46
     Татар
    0.46
     Snake
    0.46
     पान
    0.46
    Activations Density 0.000%

    No Known Activations