© 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. 195024
    Prev
    Next
    INDEX
    Explanations

    send flowers to family of

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

    just add

    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
    Zulu
    0.49
    DataProvider
    0.46
    ByMerging
    0.45
    ‚¬
    0.44
    Install
    0.43
     যাচাই
    0.43
     specialist
    0.43
    CRC
    0.43
     사용
    0.43
    URNIZOR
    0.42
    POSITIVE LOGITS
    وا
    0.50
    джа
    0.50
     nonostante
    0.46
     gonna
    0.45
    니
    0.44
     mesela
    0.44
     certes
    0.43
     รวมถึง
    0.43
     Gonna
    0.43
    バ
    0.42
    Activations Density 0.001%

    No Known Activations