© 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. 221639
    Prev
    Next
    INDEX
    Explanations

    questions, AWS, code

    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
     mav
    0.41
     superhuman
    0.41
     tourists
    0.40
     表
    0.40
     ecos
    0.40
     longue
    0.40
     brutality
    0.40
     inspectors
    0.40
     turista
    0.40
     അവര്‍
    0.39
    POSITIVE LOGITS
    alk
    0.42
    沼
    0.38
     Wesleyan
    0.36
    nodes
    0.36
    事实
    0.35
    stored
    0.35
    鑼
    0.35
    vely
    0.35
     XPath
    0.35
    Juris
    0.35
    Activations Density 0.000%

    No Known Activations