© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12088
    Prev
    Next
    INDEX
    Explanations

    excluding items or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ற்புத
    3.26
     увагу
    3.04
     Soll
    2.88
    боро
    2.87
     continueRoutine
    2.75
    bells
    2.72
    ளாக்
    2.72
    崙
    2.68
    कानेर
    2.67
    त्रेयी
    2.64
    POSITIVE LOGITS
    ele
    2.42
    ﻯ
    2.41
    eig
    2.39
    秽
    2.39
    ás
    2.29
    istisch
    2.28
    arithmic
    2.22
     //
    2.18
    িবে
    2.18
    స్‌
    2.18
    Activations Density 0.001%

    No Known Activations