© 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. 177543
    Prev
    Next
    INDEX
    Explanations

    injury, populations, narrative

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

    detection, predictive, comparative, crisis, section

    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
     Texans
    0.49
    ammers
    0.48
     postoperative
    0.47
     concealing
    0.47
     Backyard
    0.46
    <0x99>
    0.45
     Fixing
    0.44
     Jó
    0.44
    mers
    0.43
    etzungen
    0.43
    POSITIVE LOGITS
     proviene
    0.56
    드
    0.52
     яким
    0.49
     প্রযুক্ত
    0.49
     poin
    0.48
     በላይ
    0.48
     ねえ
    0.46
    普及
    0.46
     '*'
    0.46
     토
    0.46
    Activations Density 0.000%

    No Known Activations