© 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. 825
    Prev
    Next
    INDEX
    Explanations

    foreign language starters

    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
     Authentication
    1.09
     exaggerate
    1.07
    ometries
    1.07
    𝐍
    1.05
     replicate
    1.03
    াবহ
    1.02
    Physics
    1.02
    Listeners
    1.02
    ומים
    1.01
    ActivityCompat
    1.01
    POSITIVE LOGITS
    kaan
    1.25
    お
    1.22
     adı
    1.21
    ры
    1.20
    uuuu
    1.17
    k
    1.17
    unordered
    1.15
    មិន
    1.14
     territoire
    1.13
    ㅋ
    1.11
    Activations Density 0.000%

    No Known Activations