© 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. 110461
    Prev
    Next
    INDEX
    Explanations

    kontinpartidonduomenencontrolar경우determineshall形象

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

    afford Chemical, maps package

    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
     fertilizers
    0.49
     گھ
    0.47
     mixers
    0.46
    Refund
    0.44
    ށ
    0.43
    혔
    0.43
    Markets
    0.43
    στά
    0.42
     Supporters
    0.42
    ၊
    0.42
    POSITIVE LOGITS
     kontin
    0.52
     parti
    0.51
    don
    0.51
     duomen
    0.48
    en
    0.48
     controlar
    0.47
     경우
    0.47
    determine
    0.47
    shall
    0.46
    形象
    0.46
    Activations Density 0.001%

    No Known Activations