© 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. 132628
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    impact even property versions reason customer

    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
     不过
    0.53
    det
    0.50
    镑
    0.50
    nbhd
    0.48
    Fraction
    0.46
    鎊
    0.46
     존재하는
    0.46
    itriangular
    0.46
    ("["
    0.45
    на
    0.45
    POSITIVE LOGITS
     storytelling
    0.56
     policy
    0.50
     layered
    0.50
     serotonin
    0.49
     regimen
    0.49
     reiter
    0.49
     tom
    0.48
     quickly
    0.48
     minden
    0.47
     नीति
    0.46
    Activations Density 0.000%

    No Known Activations