© 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. 172442
    Prev
    Next
    INDEX
    Explanations

    "this one" / "of the" / "to your"

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

    not just, disrupt, hammer

    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
    -
    0.51
    TA
    0.49
    ↵↵
    0.46
     Benito
    0.45
    <0xE2>
    0.44
     Western
    0.43
     Mir
    0.43
     PRESSURE
    0.42
    лото
    0.42
    otá
    0.41
    POSITIVE LOGITS
    duled
    0.61
    စ္စည်း
    0.55
    商品を
    0.54
     सतत
    0.54
     แจ
    0.52
     ሌሎች
    0.52
     लगातार
    0.50
     सटीक
    0.49
    먀
    0.49
     よく
    0.49
    Activations Density 0.001%

    No Known Activations