© 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. 241987
    Prev
    Next
    INDEX
    Explanations

    lamp provide, westerly along, plasma tv

    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
     judiciales
    0.48
    你看
    0.48
     nacionais
    0.44
     五
    0.44
     जताया
    0.44
     ناقابل
    0.43
     आपसी
    0.43
    卑
    0.43
     setores
    0.42
     محسوس
    0.42
    POSITIVE LOGITS
     urmă
    0.46
    🌘
    0.46
     practic
    0.44
    ractor
    0.43
    arin
    0.43
    ხვევ
    0.42
    ATHER
    0.42
    ➳
    0.42
    gather
    0.41
    므로
    0.41
    Activations Density 0.001%

    No Known Activations