© 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. 2316
    Prev
    Next
    INDEX
    Explanations

    español questions

    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
     አንድ
    2.70
     allons
    2.68
    ទុក
    2.68
     gire
    2.64
    ខ្ញុំ
    2.64
     sheer
    2.63
    ږ
    2.63
    ږي
    2.63
     worsening
    2.60
     interfering
    2.60
    POSITIVE LOGITS
    ان
    2.68
    an
    2.64
    ال
    2.53
    it
    2.44
    な
    2.42
    ര
    2.42
    on
    2.36
    رة
    2.28
    he
    2.26
    ంటి
    2.24
    Activations Density 0.169%

    No Known Activations