© 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. 31-GEMMASCOPE-2-RES-262K
    7. 91449
    Prev
    Next
    INDEX
    Explanations

    friendly librarians and adventurers

    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_31_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
    叠加
    0.43
    ွန်
    0.42
    典型的
    0.42
    Offer
    0.41
     arquitectura
    0.41
    صر
    0.41
    ৫
    0.41
    )=(-
    0.40
    عه
    0.40
    Einzel
    0.40
    POSITIVE LOGITS
     abstinence
    0.49
    oreg
    0.47
     friends
    0.46
     mountaine
    0.45
     leisurely
    0.45
     lightening
    0.45
    ier
    0.44
    กีฬา
    0.44
    ain
    0.44
     நண்ப
    0.44
    Activations Density 0.004%

    No Known Activations