© 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-16K
    7. 1334
    Prev
    Next
    INDEX
    Explanations

    social media, programming, geography, history, food

    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_16k_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
    ו
    1.37
    ت
    1.36
    yard
    1.35
    venidos
    1.25
    gestion
    1.23
    ு
    1.20
     respectivos
    1.16
    تى
    1.15
     tp
    1.14
    OUGH
    1.14
    POSITIVE LOGITS
     hinged
    1.29
    ق
    1.29
     tampa
    1.28
    င
    1.26
    ремя
    1.23
    ف
    1.23
    ᠨ
    1.21
    rk
    1.21
     tvor
    1.19
    alien
    1.19
    Activations Density 0.202%

    No Known Activations