© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    you to

    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
    rangian
    2.99
    alakip
    2.99
    ृती
    2.96
     утра
    2.88
    𝒖
    2.86
     kinases
    2.84
     perishable
    2.83
     ”,
    2.83
    iverr
    2.83
    𝒐
    2.82
    POSITIVE LOGITS
    ung
    2.88
    UNG
    2.72
    sschutz
    2.69
    pi
    2.59
    ungen
    2.57
     '
    2.21
    se
    2.21
    ᅧ
    2.15
    ungnya
    2.14
    neath
    2.09
    Activations Density 0.144%

    No Known Activations