© 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. 114609
    Prev
    Next
    INDEX
    Explanations

    already

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

    already

    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
     কতক
    0.40
    लक
    0.40
    ഭാഗ
    0.39
     Ген
    0.38
     späteren
    0.38
    ैल
    0.38
    럇
    0.38
    nacht
    0.38
    耠
    0.38
    豇
    0.37
    POSITIVE LOGITS
     already
    1.11
     Already
    1.09
    Already
    1.04
    already
    0.97
     ऑलरेडी
    0.95
     এমনি
    0.91
    已经是
    0.91
     уже
    0.88
     allerede
    0.85
     zaten
    0.84
    Activations Density 0.194%

    No Known Activations