© 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. 13842
    Prev
    Next
    INDEX
    Explanations

    lake

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

    recognizing specific vocabulary

    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
     några
    0.52
     namelijk
    0.48
     använda
    0.48
     상세
    0.48
     آف
    0.48
     розташо
    0.47
    󰀄
    0.47
     menghubungi
    0.46
    ᥙ
    0.45
    Ꮒ
    0.45
    POSITIVE LOGITS
    ;
    0.51
    ,
    0.46
    ;#
    0.46
    aneswar
    0.45
     Focus
    0.44
    rooted
    0.43
     Recognizing
    0.42
     рецен
    0.42
     கவனம்
    0.41
    ؛
    0.41
    Activations Density 0.000%

    No Known Activations