© 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. 11174
    Prev
    Next
    INDEX
    Explanations

    neutron

    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
    ra
    2.39
    <bos>
    2.34
    δ
    2.31
    ुसार
    2.31
    amen
    2.30
    werte
    2.29
    ings
    2.27
    岖
    2.26
    aturen
    2.25
    ैव
    2.25
    POSITIVE LOGITS
    kz
    2.76
    к
    2.68
     кушымта
    2.63
     cuttings
    2.62
    drain
    2.62
     Swal
    2.62
    dioxide
    2.60
     îng
    2.59
    tR
    2.59
    zou
    2.58
    Activations Density 0.004%

    No Known Activations