© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    Scanner

    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
    А
    2.61
    jenigen
    2.51
    ر
    2.48
    нія
    2.45
     continents
    2.29
     недоста
    2.26
     ganz
    2.23
     tret
    2.23
    е
    2.22
    Интернет
    2.19
    POSITIVE LOGITS
    क
    3.73
    as
    3.73
    
    3.12
    ia
    3.01
    EditorGUI
    2.96
    ым
    2.89
    ի
    2.87
    ை
    2.86
    k
    2.81
    ни
    2.74
    Activations Density 0.005%

    No Known Activations