© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    understanding context and relationships

    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
    ن
    2.75
    ība
    2.66
    ību
    2.60
    ոչ
    2.55
    ్రు
    2.53
    راہیم
    2.47
    嗐
    2.39
    བ
    2.38
    梠
    2.37
     COURSE
    2.36
    POSITIVE LOGITS
    스코
    2.49
    sing
    2.48
    ी
    2.40
    s
    2.39
    sat
    2.36
    ept
    2.36
    閉
    2.28
    ppins
    2.27
    ングラス
    2.21
    ptu
    2.17
    Activations Density 0.015%

    No Known Activations