© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12218
    Prev
    Next
    INDEX
    Explanations

    Linear Elastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $\{(
    0.45
     ხელ
    0.44
    ಥ
    0.44
    ்ட
    0.43
     редакти
    0.43
    eneral
    0.43
    ue
    0.42
     سلس
    0.42
     eup
    0.42
    ٴ
    0.42
    POSITIVE LOGITS
    ENV
    0.44
     pledge
    0.39
     écologique
    0.39
     ENV
    0.39
    ANK
    0.38
    襁
    0.38
     pageant
    0.38
    env
    0.38
     JavaScript
    0.38
     academies
    0.38
    Activations Density 0.000%

    No Known Activations