© 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. 243136
    Prev
    Next
    INDEX
    Explanations

    system, family, there, the, that, worker

    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
    та
    0.50
    us
    0.48
    ק
    0.47
    ພວກເຮົາ
    0.46
    comma
    0.45
    ropolitana
    0.45
     COLLISIONS
    0.45
     headquartered
    0.45
    zr
    0.45
    igamma
    0.44
    POSITIVE LOGITS
     {[
    0.46
     قام
    0.45
     musí
    0.44
     æ
    0.43
    ऽ
    0.42
     rô
    0.42
     définit
    0.42
     før
    0.42
    ว์
    0.41
     závod
    0.41
    Activations Density 0.000%

    No Known Activations