© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    word endings from various languages

    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
    н
    4.25
    speople
    4.24
    ン
    4.22
     irreducible
    3.54
    ively
    3.51
     tarsi
    3.28
    ️
    3.25
    으로
    3.19
    ন
    3.08
    ट
    3.03
    POSITIVE LOGITS
    ्स
    4.37
    tta
    4.13
    lla
    3.96
    lle
    3.84
    gg
    3.80
    chen
    3.68
    tti
    3.56
    chnung
    3.51
    deki
    3.47
    czny
    3.45
    Activations Density 0.189%

    No Known Activations