© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    here are or here's

    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
    2.54
    kans
    2.37
    g
    2.21
    punten
    2.19
    discharge
    2.19
    c
    2.17
    p
    2.17
    те
    2.14
    יר
    2.14
    ou
    2.13
    POSITIVE LOGITS
    ্সের
    2.58
    𝗍
    2.35
    夕
    2.33
     ইলে
    2.32
    หว่าง
    2.31
     instruções
    2.31
    匐
    2.31
    কারীর
    2.29
    兮
    2.28
    ロジー
    2.26
    Activations Density 0.151%

    No Known Activations