© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172528
    Prev
    Next
    INDEX
    Explanations

    legal, technical, or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite

    more, most, less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     To
    0.52
     Với
    0.52
     Perhaps
    0.50
     Analog
    0.50
     Possibly
    0.49
     integrity
    0.48
    ೇವೆ
    0.48
     だ
    0.48
     aliquot
    0.48
     Distinct
    0.47
    POSITIVE LOGITS
    DrawerToggle
    0.49
    ")}}'
    0.46
    ୯
    0.46
    വ്വ
    0.44
    rimi
    0.43
    Disable
    0.42
    Shot
    0.41
     মানে
    0.40
    ProductImages
    0.40
    ativa
    0.40
    Activations Density 0.000%

    No Known Activations