© 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. 32950
    Prev
    Next
    INDEX
    Explanations

    foreign terms and specific phrases

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

    divergence, discontinuities, communities, little

    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
    rocess
    0.50
    მართ
    0.47
    lias
    0.47
    ⊆
    0.45
     fulfils
    0.44
    UIS
    0.44
     Grows
    0.43
     arco
    0.42
     disseminate
    0.42
     Blaze
    0.42
    POSITIVE LOGITS
     জরিমানা
    0.50
    ag
    0.50
     термин
    0.49
    郓
    0.48
    брать
    0.46
     трени
    0.46
     jub
    0.46
     desac
    0.46
     MacL
    0.46
     название
    0.46
    Activations Density 0.000%

    No Known Activations