© 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. 22756
    Prev
    Next
    INDEX
    Explanations

    open and click

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

    device messages

    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
     ぐらい
    0.44
     どれ
    0.44
     ورلڈ
    0.44
     けれど
    0.43
     bilangan
    0.42
    encode
    0.42
     എത്ര
    0.42
     {$
    0.42
     spitting
    0.41
     )$
    0.41
    POSITIVE LOGITS
     devices
    0.55
    Devices
    0.54
     Devices
    0.51
     DEVICES
    0.49
    devices
    0.47
     устройств
    0.46
    Mechanism
    0.46
    TURN
    0.45
     устройства
    0.45
    جهزة
    0.44
    Activations Density 0.002%

    No Known Activations