© 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. 168322
    Prev
    Next
    INDEX
    Explanations

    web page structure and navigation

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

    HTML button elements and attributes

    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
    諄
    0.52
    Muj
    0.47
    適切
    0.45
     برضو
    0.45
     barato
    0.44
     viviendo
    0.42
     SMEs
    0.42
     ವೈ
    0.42
     предпринима
    0.41
    sufficient
    0.41
    POSITIVE LOGITS
     퍼
    0.47
     पर्
    0.44
     hid
    0.43
     clientId
    0.40
     フレ
    0.40
    innerHTML
    0.39
     fed
    0.39
     feeds
    0.39
     régl
    0.39
     rod
    0.38
    Activations Density 0.002%

    No Known Activations