© 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. 216732
    Prev
    Next
    INDEX
    Explanations

    strobe light

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

    hidden layers and ai

    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
    b
    0.50
    くらいの
    0.47
     or
    0.47
     অ
    0.46
     a
    0.45
    ள்
    0.45
     Oracle
    0.44
    g
    0.44
    ཇ
    0.44
    é
    0.43
    POSITIVE LOGITS
     lovingly
    0.51
    ampions
    0.45
     plaatsen
    0.45
     localize
    0.44
    <unused21>
    0.44
    egang
    0.44
    IUpdate
    0.44
    ͛
    0.44
     prosecute
    0.44
    ]*(
    0.44
    Activations Density 0.001%

    No Known Activations