© 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. 25988
    Prev
    Next
    INDEX
    Explanations

    describing color attributes

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

    moral argument, usually labeled

    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
    そのような
    0.47
     होऊन
    0.43
    xlsx
    0.41
    ского
    0.41
    ен
    0.40
    teaching
    0.40
    财
    0.40
    arai
    0.40
    recorded
    0.40
     نسبت
    0.40
    POSITIVE LOGITS
     playgrounds
    0.46
    电源
    0.43
    otene
    0.42
     안정
    0.41
     화면
    0.41
     veřej
    0.41
    жность
    0.40
     blanchâtre
    0.40
     ścian
    0.39
    <unused53>
    0.39
    Activations Density 0.000%

    No Known Activations