© 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. 96144
    Prev
    Next
    INDEX
    Explanations

    invitation to learn or find

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

    finding or using phrases

    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
    韵
    0.47
     I
    0.45
     history
    0.44
     ";
    0.44
    菏
    0.43
     portland
    0.43
     nanotechnology
    0.43
     Loyalty
    0.42
     Lampung
    0.41
     loy
    0.41
    POSITIVE LOGITS
    desde
    0.55
     facteur
    0.53
    mittent
    0.51
    thrombin
    0.51
    ()],
    0.50
    ק
    0.50
     நக
    0.50
    carb
    0.49
    cemia
    0.49
     один
    0.47
    Activations Density 0.001%

    No Known Activations