© 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. 247443
    Prev
    Next
    INDEX
    Explanations

    payment or profits

    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
    i
    0.50
    im
    0.50
    t
    0.47
    ator
    0.47
     Read
    0.47
     In
    0.46
     aside
    0.45
    _
    0.41
    ol
    0.41
     Cork
    0.41
    POSITIVE LOGITS
    OVERRIDES
    0.50
    襷
    0.49
    喧
    0.49
    ネルギー
    0.48
    られる
    0.47
    들과
    0.46
    蔘
    0.46
     शक्ती
    0.45
     충
    0.45
    ренный
    0.45
    Activations Density 0.000%

    No Known Activations