© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    MoMA, Rickroll URLs, JN.1, sporting tactical

    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
    ट
    1.58
    er
    1.47
    ت
    1.46
    र
    1.38
    ർ
    1.38
    り
    1.31
    ര്‍
    1.28
    х
    1.28
    YE
    1.26
     সঞ্জ
    1.25
    POSITIVE LOGITS
     tropas
    1.54
    thousand
    1.53
    larını
    1.51
    teenth
    1.51
     helst
    1.49
     consecuencias
    1.49
    larına
    1.45
    ları
    1.45
     rodas
    1.43
     ony
    1.43
    Activations Density 0.001%

    No Known Activations