© 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. 51203
    Prev
    Next
    INDEX
    Explanations

    recent events and accomplishments

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

    Reduced Estrogen Effect

    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
    将军
    0.48
    բ
    0.48
     अक्टूबर
    0.44
    だけで
    0.44
     responsibly
    0.44
    idescent
    0.43
    革命
    0.43
    市立
    0.42
    🇴
    0.42
    !).
    0.42
    POSITIVE LOGITS
     удовлетво
    0.49
     最近
    0.45
    isi
    0.45
     upas
    0.43
     موفق
    0.42
    kval
    0.42
    acidad
    0.42
     đầy
    0.41
    ToString
    0.41
     wechsel
    0.41
    Activations Density 0.000%

    No Known Activations