© 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. 91861
    Prev
    Next
    INDEX
    Explanations

    product offerings

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

    sunrise, grace, and hue

    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
     I
    0.52
    $\$
    0.45
    ਤੇ
    0.44
    s
    0.44
    i
    0.44
     protective
    0.43
    ied
    0.42
     technological
    0.42
    stechn
    0.42
    h
    0.41
    POSITIVE LOGITS
     본격
    0.49
    timelist
    0.44
     infraestructura
    0.44
     ফাঁস
    0.44
    本格
    0.43
     fenómenos
    0.43
    제를
    0.42
     Ан
    0.42
     stripped
    0.42
    軼
    0.41
    Activations Density 0.000%

    No Known Activations