© 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. 68664
    Prev
    Next
    INDEX
    Explanations

    something different

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

    mathematical and symbolic notation

    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
    ล
    0.50
     உற்ப
    0.47
     crescere
    0.47
     уверен
    0.47
    तरह
    0.46
    SEASON
    0.46
     üret
    0.45
    IVER
    0.45
    症
    0.45
    งาม
    0.44
    POSITIVE LOGITS
     شاه
    0.51
     mobiles
    0.45
     Divided
    0.45
    (−
    0.45
     palettes
    0.43
    ంచెం
    0.43
     mía
    0.42
    érés
    0.42
     Owned
    0.42
     Apo
    0.41
    Activations Density 0.001%

    No Known Activations