© 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. 134827
    Prev
    Next
    INDEX
    Explanations

    brain and influencing concepts

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

    Bubble Hash, White buttons

    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
     Η
    0.57
     உண்மைய
    0.51
    oul
    0.50
    uldu
    0.50
    <0x80>
    0.49
    umbled
    0.49
    ioi
    0.49
    ư
    0.48
     Τ
    0.47
     Sotheby
    0.47
    POSITIVE LOGITS
    大脑
    0.46
    нями
    0.45
    цтва
    0.44
     kann
    0.43
    影响
    0.43
    туры
    0.43
    ESTER
    0.43
     buds
    0.43
    Brain
    0.43
    gewicht
    0.43
    Activations Density 0.000%

    No Known Activations