© 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. 12069
    Prev
    Next
    INDEX
    Explanations

    again

    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
     tendance
    1.47
     welke
    1.46
    Το
    1.35
    Ш
    1.33
    फोटो
    1.31
     noch
    1.29
    Jetzt
    1.28
     permettant
    1.28
    impanan
    1.26
     kaikki
    1.24
    POSITIVE LOGITS
    ्हा
    1.27
    ❤️❤️
    1.20
     pilgrimage
    1.20
     Meteorological
    1.19
    iagn
    1.18
    iencing
    1.18
     Dragons
    1.17
     dragons
    1.15
    isht
    1.14
    ва
    1.13
    Activations Density 0.000%

    No Known Activations