© 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. 2305
    Prev
    Next
    INDEX
    Explanations

    two and related entities

    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
    theless
    1.49
    اً
    1.47
    ieurs
    1.47
    ियों
    1.45
    ين
    1.31
     strollers
    1.27
    pośred
    1.22
    もら
    1.20
    tain
    1.20
    ständig
    1.19
    POSITIVE LOGITS
    ed
    1.61
    ा
    1.48
     thirds
    1.41
    ة
    1.41
    en
    1.29
    ు
    1.25
    наў
    1.24
    ي
    1.15
     eens
    1.12
    thirds
    1.11
    Activations Density 0.073%

    No Known Activations