© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    ST prefix exam codes

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

    AI in RTS games

    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
     অফিস
    0.52
    兖
    0.52
     kmeans
    0.48
     shootings
    0.46
    Ỡ
    0.46
     সিরিজের
    0.45
    グラ
    0.45
    ের
    0.45
    數
    0.45
    ંપની
    0.44
    POSITIVE LOGITS
    king
    0.45
    <0xB7>
    0.44
    omel
    0.43
     )
    0.43
    fühl
    0.42
    推动
    0.42
    abandon
    0.42
    uber
    0.41
    Alexis
    0.41
    cub
    0.41
    Activations Density 0.000%

    No Known Activations