© 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. 104150
    Prev
    Next
    INDEX
    Explanations

    HealthDay News

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

    states and circumstances

    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
     Confira
    0.47
     comerci
    0.44
    4
    0.42
    $%
    0.41
     Kelly
    0.40
     Faro
    0.40
    in
    0.40
    empt
    0.40
     Liza
    0.40
    ẹ
    0.40
    POSITIVE LOGITS
    造成的
    0.49
    の状態
    0.48
     അവസ്ഥ
    0.47
     ప్రభావ
    0.46
     ایجاد
    0.46
     تاثیر
    0.45
    पत्नी
    0.45
    変数
    0.44
    の影響
    0.44
     astronomers
    0.43
    Activations Density 0.002%

    No Known Activations