© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    Wait active, hot reload, story hooks, loft feature

    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
    s
    3.51
    t
    3.11
    ي
    3.10
    tım
    2.90
    sab
    2.78
    sides
    2.75
    trom
    2.71
    ০
    2.70
    tif
    2.65
    т
    2.63
    POSITIVE LOGITS
    𝐠
    3.02
    𝓗
    2.91
    ایط
    2.90
    ल्याण
    2.81
    adType
    2.76
    ︎
    2.76
    𝑂
    2.74
    𝐸
    2.71
    𝕚
    2.69
    ণ্ঠে
    2.68
    Activations Density 0.006%

    No Known Activations