© 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. 11316
    Prev
    Next
    INDEX
    Explanations

    navigating

    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
    د
    1.48
    ce
    1.46
    brides
    1.36
     ActionListener
    1.35
    Sentiment
    1.35
    midi
    1.32
    yh
    1.30
    με
    1.27
    withstanding
    1.27
    𝒶
    1.26
    POSITIVE LOGITS
    どの
    1.35
     себя
    1.35
    ਿਕ
    1.33
    ்ட்
    1.32
     muestran
    1.30
     ਕਿ
    1.25
     необходимо
    1.25
    ডিয়া
    1.24
    ين
    1.23
    ння
    1.22
    Activations Density 0.000%

    No Known Activations