© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12910
    Prev
    Next
    INDEX
    Explanations

    points and marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scattering
    2.28
    er
    2.24
    र
    2.22
    ্ষ
    2.21
    kező
    2.18
    loss
    2.17
    unjukkan
    2.15
    一層
    2.13
    lidir
    2.12
    eliti
    2.11
    POSITIVE LOGITS
    Св
    2.88
    ifix
    2.75
    ȱ
    2.72
    Ắ
    2.71
    NewLabel
    2.70
     +:+
    2.69
    𝖎
    2.67
    舝
    2.63
    骨
    2.60
    דר
    2.58
    Activations Density 0.003%

    No Known Activations