© 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. 12984
    Prev
    Next
    INDEX
    Explanations

    score indicator

    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
    icur
    3.25
     naan
    3.16
    maligngroup
    3.06
    -_
    3.04
    یع
    2.99
    يلي
    2.98
    nehmen
    2.94
    勬
    2.94
    itôt
    2.90
     निभा
    2.85
    POSITIVE LOGITS
    ோ
    2.30
    ete
    2.22
    빼
    2.20
     recoge
    2.14
    webtoken
    2.12
    ㄺ
    2.07
    ╲
    2.05
    Baca
    2.00
     목
    1.99
    ோவில்
    1.99
    Activations Density 0.017%

    No Known Activations