© 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. 41-GEMMASCOPE-2-RES-262K
    7. 197674
    Prev
    Next
    INDEX
    Explanations

    code snippets in English

    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_all/layer_41_width_262k_l0_big
    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
     Ahm
    0.51
     pravil
    0.45
     cosine
    0.45
     zero
    0.45
     name
    0.44
     ozn
    0.44
    Ğ
    0.44
     Gr
    0.44
     freight
    0.44
     government
    0.42
    POSITIVE LOGITS
    expenses
    0.47
    macosx
    0.44
    烬
    0.42
    やく
    0.41
     Subdistrict
    0.41
    jobNumber
    0.40
    WebElement
    0.40
    recording
    0.40
     بیشتری
    0.39
     creases
    0.39
    Activations Density 0.194%

    No Known Activations