© 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. 136891
    Prev
    Next
    INDEX
    Explanations

    tables and code examples

    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
    ik
    0.43
    further
    0.39
     Ayrıca
    0.38
    k
    0.37
    í
    0.37
    including
    0.37
    also
    0.37
    ike
    0.36
    keep
    0.36
    ð
    0.36
    POSITIVE LOGITS
     metamorphosis
    0.38
     tumult
    0.37
     برد
    0.37
     ferrite
    0.36
    יים
    0.36
    COVERY
    0.35
     shoots
    0.35
     kép
    0.35
     centrality
    0.35
     coalescence
    0.35
    Activations Density 0.031%

    No Known Activations