© 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. 131740
    Prev
    Next
    INDEX
    Explanations

    even if, who among, your project

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

    Who is

    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
    مي
    0.51
    йдз
    0.50
    الأ
    0.50
    ид
    0.50
    achtige
    0.49
    мо
    0.48
    מ
    0.48
    ზ
    0.48
     mismas
    0.47
     Frühstück
    0.47
    POSITIVE LOGITS
     owing
    0.49
    СР
    0.47
    ​
    0.44
     stride
    0.43
    ILE
    0.43
     ast
    0.42
     секу
    0.42
     espont
    0.42
    狈
    0.42
    ​.
    0.41
    Activations Density 0.001%

    No Known Activations