© 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. 126839
    Prev
    Next
    INDEX
    Explanations

    thank you, URL, rights

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

    arm, yeast, page, bikes, human

    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
     Undert
    0.54
    学院
    0.48
    ണ
    0.48
    选手
    0.47
     Equilib
    0.47
    संह
    0.46
    躏
    0.46
    胙
    0.45
    घाडी
    0.45
     Overlay
    0.45
    POSITIVE LOGITS
    ):
    0.51
    bytes
    0.49
     grandmother
    0.48
    adas
    0.48
    se
    0.47
    itor
    0.47
     merveille
    0.47
    .).
    0.47
     prowess
    0.47
    ollow
    0.46
    Activations Density 0.002%

    No Known Activations