© 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. 99333
    Prev
    Next
    INDEX
    Explanations

    special status

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

    state/reaction/description

    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
    ♰
    0.52
    وات
    0.50
     言っ
    0.49
    دیا
    0.47
    وہ
    0.45
    /-/
    0.45
     مثال
    0.44
     предполага
    0.44
     curviliné
    0.44
    ியாக
    0.44
    POSITIVE LOGITS
    </h3>
    0.48
     continu
    0.45
    kušen
    0.44
    teres
    0.44
     hardworking
    0.44
    loos
    0.44
     turbulent
    0.43
    преде
    0.42
    doesn
    0.42
    ↵↵
    0.42
    Activations Density 0.001%

    No Known Activations