© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    bullet points and symbols

    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
     불구하고
    1.58
    ੍ਹ
    1.54
    izzazione
    1.48
     sarcastic
    1.43
    а
    1.41
    ৭
    1.34
    ,'
    1.32
    르는
    1.31
    е
    1.31
     spur
    1.30
    POSITIVE LOGITS
    ه
    2.42
    as
    2.24
    ات
    2.21
    ী
    2.14
    ة
    2.12
    ের
    2.10
    l
    2.08
    at
    2.06
    ה
    2.04
    is
    2.03
    Activations Density 0.423%

    No Known Activations