© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    allows you to

    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
    l
    1.68
    ка
    1.36
    te
    1.34
    ل
    1.29
    ל
    1.29
    in
    1.20
    ε
    1.13
    לים
    1.13
    د
    1.12
    nur
    1.12
    POSITIVE LOGITS
    Ⲓ
    1.41
    써
    1.40
    ી
    1.36
    statusCode
    1.35
     жителей
    1.33
    <0xD0>
    1.31
    Ⲧ
    1.31
    isInt
    1.30
     chills
    1.30
    ᐋ
    1.29
    Activations Density 0.435%

    No Known Activations