© 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. 173346
    Prev
    Next
    INDEX
    Explanations

    foundation

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

    adore, fails, require, survive

    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
     mysticism
    0.47
    较高的
    0.47
    ந்த
    0.46
     estratég
    0.45
     vět
    0.45
    狀
    0.45
    骚
    0.44
     lacus
    0.43
    нов
    0.42
     спри
    0.42
    POSITIVE LOGITS
    t
    0.50
     Multipart
    0.50
     Khark
    0.49
     Agra
    0.49
     a
    0.47
     Watercolour
    0.47
     Mira
    0.47
     Jaipur
    0.46
     Galicia
    0.45
     Multip
    0.45
    Activations Density 0.000%

    No Known Activations