© 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. 12776
    Prev
    Next
    INDEX
    Explanations

    Montserrat as font example

    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
    ാ
    3.36
    ি
    3.15
    y
    3.09
    es
    2.87
    ে
    2.84
    ی
    2.73
    ു
    2.69
    yen
    2.63
    yra
    2.56
     čemu
    2.51
    POSITIVE LOGITS
    🆈
    2.69
    蜍
    2.66
    zept
    2.52
    gister
    2.52
    pcl
    2.45
    FileAlignment
    2.41
    ॉजी
    2.39
    den
    2.37
    াবণ
    2.29
     Past
    2.27
    Activations Density 0.023%

    No Known Activations