© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9824
    Prev
    Next
    INDEX
    Explanations

    Amharic characters and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preposition
    1.62
     Использу
    1.54
    й
    1.51
     ока
    1.51
    jenigen
    1.50
    তা
    1.43
     preso
    1.42
    п
    1.41
    произ
    1.40
    ≖
    1.39
    POSITIVE LOGITS
    the
    1.79
    tting
    1.63
    st
    1.54
    engono
    1.49
    nya
    1.40
    స్‌
    1.38
    מ
    1.37
    theit
    1.33
    rary
    1.32
    naam
    1.32
    Activations Density 0.000%

    No Known Activations