© 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. 9730
    Prev
    Next
    INDEX
    Explanations

    coding configurations and security

    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
    द
    1.55
    cía
    1.52
    cido
    1.51
    Aunque
    1.50
    iendo
    1.48
    mente
    1.47
    prisingly
    1.46
    ción
    1.43
     Dioxide
    1.42
    ciones
    1.40
    POSITIVE LOGITS
     проходи
    1.27
    ます
    1.27
    깔
    1.22
    others
    1.21
    hoe
    1.20
     Windsor
    1.20
     fruition
    1.18
     اختيار
    1.14
     koordin
    1.13
     debunk
    1.13
    Activations Density 0.000%

    No Known Activations