© 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. 22520
    Prev
    Next
    INDEX
    Explanations

    representing states, rows, or data

    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
     విషయం
    0.38
    凜
    0.38
     രംഗ
    0.37
    这话
    0.37
    湡
    0.37
    ingan
    0.37
     folos
    0.36
    <unused65>
    0.35
     cucumbers
    0.35
     مجبور
    0.35
    POSITIVE LOGITS
     representing
    2.80
     represents
    2.72
     represent
    2.67
    representing
    2.50
     Represents
    2.41
     representando
    2.41
     representan
    2.38
    represents
    2.36
     representar
    2.33
     Represent
    2.31
    Activations Density 0.004%

    No Known Activations