© 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. 61577
    Prev
    Next
    INDEX
    Explanations

    video game maker

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

    processor family, pcb board, gaming, code, universies, gradle

    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
     conundrum
    0.39
     abruptly
    0.38
     fearing
    0.38
    <0xE2>
    0.37
     acclaim
    0.37
    مل
    0.37
     acumen
    0.37
    ↵↵
    0.36
     دیگر
    0.36
    گ
    0.35
    POSITIVE LOGITS
     график
    0.46
    рб
    0.45
    lawn
    0.45
    废水
    0.45
    offers
    0.43
    ونها
    0.42
    graphics
    0.42
    addena
    0.42
     rất
    0.41
    awarkan
    0.41
    Activations Density 0.000%

    No Known Activations