© 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. 190894
    Prev
    Next
    INDEX
    Explanations

    freshness remains

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

    considering me

    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
    লি
    0.45
     सीसीटीवी
    0.45
    सभी
    0.45
    ็ม
    0.45
    ﺛ
    0.45
     postérieur
    0.44
    ل
    0.44
    áme
    0.44
    ৬
    0.43
     હત્યા
    0.43
    POSITIVE LOGITS
     robot
    0.49
     erwart
    0.47
     extraordinaire
    0.46
     propriety
    0.45
    parad
    0.44
     Robot
    0.43
    robot
    0.42
     Laura
    0.41
    seur
    0.41
    etze
    0.41
    Activations Density 0.000%

    No Known Activations