© 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. 77070
    Prev
    Next
    INDEX
    Explanations

    situated or located in

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

    html lang attribute

    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
    𝐤
    0.49
    𝚓
    0.48
     রাস্তায়
    0.47
     Juice
    0.45
     Evaluation
    0.45
     Hy
    0.45
    ymi
    0.44
     مای
    0.43
     juice
    0.43
    ї
    0.43
    POSITIVE LOGITS
     podía
    0.49
     chapters
    0.48
     communique
    0.47
     pasó
    0.45
     serii
    0.45
     obten
    0.43
    得到了
    0.43
    监听
    0.42
    注释
    0.41
     datac
    0.41
    Activations Density 0.000%

    No Known Activations