© 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. 126220
    Prev
    Next
    INDEX
    Explanations

    purchasing a new permit

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

    capture 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
    ର
    0.52
    ра
    0.50
    キラ
    0.50
     ର
    0.49
    ル
    0.49
     まず
    0.48
    エコ
    0.47
    л
    0.47
    тива
    0.46
    名を
    0.46
    POSITIVE LOGITS
    Há
    0.50
     περίπτωση
    0.50
     scrot
    0.45
    werte
    0.44
    ıt
    0.43
    现
    0.42
     Há
    0.42
    贸易
    0.41
     চোখ
    0.41
    ahrt
    0.41
    Activations Density 0.000%

    No Known Activations