© 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. 220370
    Prev
    Next
    INDEX
    Explanations

    party package

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

    definition of word

    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
     disponer
    0.55
    цька
    0.50
    лення
    0.50
    ת
    0.49
     .'
    0.48
     строительства
    0.48
    ユ
    0.48
    אן
    0.47
    лук
    0.47
     дверей
    0.47
    POSITIVE LOGITS
     hinaus
    0.53
     Olm
    0.51
     Elat
    0.49
     Hell
    0.47
     Artemis
    0.46
     Amazing
    0.46
     সময়ে
    0.45
     inim
    0.45
     Hamburg
    0.44
     Hag
    0.43
    Activations Density 0.000%

    No Known Activations