© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    AI tasks

    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
    alaman
    1.85
    fillText
    1.69
     synes
    1.68
    ங்கிணை
    1.66
    ্বিক
    1.65
    etzt
    1.60
    ྕ
    1.60
    indian
    1.60
    vet
    1.60
    ailing
    1.58
    POSITIVE LOGITS
    ت
    2.88
    𝒆
    2.43
    iendo
    2.34
    taker
    2.29
    ಯಲ್ಲಿ
    2.27
     което
    2.25
    От
    2.24
    ה
    2.24
    <bos>
    2.16
    ת
    2.11
    Activations Density 0.085%

    No Known Activations