© 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. 221343
    Prev
    Next
    INDEX
    Explanations

    often bundle

    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
     resemblance
    0.41
     similarity
    0.41
    荸
    0.39
     Prism
    0.39
     macaroni
    0.38
     nigdy
    0.38
     አይደለም
    0.38
     Similarity
    0.38
     Servlet
    0.38
     Christus
    0.38
    POSITIVE LOGITS
     hẹn
    0.39
    倖
    0.39
    預
    0.38
    ֥
    0.38
    ີ່ມ
    0.37
    预
    0.37
     phổ
    0.35
     Either
    0.35
    ිත
    0.35
    ounds
    0.35
    Activations Density 0.000%

    No Known Activations