© 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. 67661
    Prev
    Next
    INDEX
    Explanations

    specific words and numbers

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

    Declarative memory

    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
    ibul
    0.50
    icip
    0.46
    ahit
    0.45
     teinte
    0.45
    icient
    0.44
    orde
    0.44
    عل
    0.44
    :~
    0.44
    iese
    0.43
    yle
    0.43
    POSITIVE LOGITS
     may
    0.54
     overlaps
    0.49
     are
    0.48
     as
    0.48
     বিস্তারিত
    0.48
     Expanded
    0.48
     Да
    0.46
     Díaz
    0.46
     ব্যাপক
    0.46
    ೊಂದು
    0.46
    Activations Density 0.001%

    No Known Activations