© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    hunting behavior and style

    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
    ا
    3.21
    갓
    2.74
    ak
    2.71
    ک
    2.71
    “.
    2.60
    ic
    2.54
    اا
    2.49
    و
    2.49
    اپ
    2.45
    𝒖
    2.39
    POSITIVE LOGITS
    ᴇ
    3.53
    GLE
    3.36
    鎶
    3.35
    eglasses
    3.24
    𝑀
    3.17
    BUCK
    3.13
    佞
    3.10
    𝓟
    3.05
    (?:
    2.98
     家
    2.94
    Activations Density 0.008%

    No Known Activations