© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    want to

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

    ; surprise, chatbots, ban, service

    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
     crev
    0.45
     teníamos
    0.43
    ◸
    0.40
     રહ્યા
    0.39
     breezy
    0.39
     biofuels
    0.39
    でしたが
    0.38
    就连
    0.38
    個性
    0.38
    😸
    0.38
    POSITIVE LOGITS
    k
    0.49
     maggiore
    0.48
     memper
    0.47
     يجب
    0.43
     Transparent
    0.43
     Worse
    0.43
     Timing
    0.42
     Faster
    0.42
     Longer
    0.41
     greater
    0.40
    Activations Density 0.000%

    No Known Activations