© 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. 152468
    Prev
    Next
    INDEX
    Explanations

    relays, we, our, institutions

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

    split, regional, defending

    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
     ကို
    0.58
     mulher
    0.54
     ideia
    0.54
     verstär
    0.54
     Trustee
    0.52
     territoire
    0.51
     kív
    0.51
     腰
    0.51
     desejo
    0.50
    োত্তর
    0.50
    POSITIVE LOGITS
    8
    0.61
    F
    0.57
    9
    0.57
    compar
    0.52
    ao
    0.51
    ceed
    0.49
    Encyclopedia
    0.49
    aled
    0.48
     approximating
    0.48
    <.
    0.47
    Activations Density 0.000%

    No Known Activations