© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    slicked environments, waiting actions

    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
    theorem
    2.74
    <bos>
    2.64
    thedocs
    2.62
     Bxh
    2.60
    ২৩
    2.55
     instruct
    2.55
    原始内容
    2.54
    ১৭
    2.53
    ২১
    2.52
     Scalars
    2.52
    POSITIVE LOGITS
    ्तार
    2.64
    र
    2.44
    лле
    2.44
    composition
    2.37
    ورٹی
    2.34
    বিষ্য
    2.32
    chter
    2.29
     základě
    2.25
    दर्शक
    2.22
     cameraId
    2.20
    Activations Density 0.250%

    No Known Activations