© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    More or short descriptions

    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
    ℍ
    2.85
    𝓁
    2.70
    đ
    2.62
    ্শন
    2.59
    ลาย
    2.51
    א
    2.50
    हित्य
    2.49
    蜢
    2.49
    брав
    2.49
    ೊಳ
    2.46
    POSITIVE LOGITS
    sides
    2.75
    tok
    2.70
    "--
    2.33
    tuvo
    2.33
     sides
    2.31
    tif
    2.25
    ."-
    2.24
    ..."
    2.17
     prescriptive
    2.16
    ႉ
    2.15
    Activations Density 0.153%

    No Known Activations