© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14860
    Prev
    Next
    INDEX
    Explanations

    reading file lines

    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
    я
    2.06
     WI
    1.84
     canoe
    1.74
     that
    1.72
    ีด
    1.67
     dismiss
    1.66
    G
    1.66
    য়ে
    1.63
    ენტ
    1.60
     convey
    1.59
    POSITIVE LOGITS
    ร็จ
    2.32
    ناك
    2.17
     čtyř
    2.12
    alnız
    2.10
    目录下
    2.10
     cartera
    2.09
    sruhe
    2.08
    橐
    2.06
     yalnız
    2.05
     Maugin
    2.05
    Activations Density 0.020%

    No Known Activations