© 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. 173530
    Prev
    Next
    INDEX
    Explanations

    resident alien

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

    more followed by descriptions

    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
     பெயர்
    0.49
    зни
    0.48
    ப்பு
    0.48
     figurine
    0.48
     Aladdin
    0.48
    垲
    0.47
     конструкция
    0.46
    мни
    0.46
    幅
    0.46
    涟
    0.45
    POSITIVE LOGITS
    heim
    0.45
     تعاون
    0.45
     협
    0.45
     អ
    0.44
     सोसायटी
    0.43
    細胞
    0.43
    rib
    0.42
    useum
    0.42
    collabor
    0.41
    issenschaft
    0.40
    Activations Density 0.001%

    No Known Activations