© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    javascript:(function()

    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
    꿈
    2.00
    ιστή
    1.97
    ುದು
    1.84
    pload
    1.82
     halus
    1.82
    ilation
    1.79
    phant
    1.69
    legt
    1.66
    BitCount
    1.66
    isle
    1.65
    POSITIVE LOGITS
     insc
    2.41
    藤
    2.37
    FJ
    2.18
    resti
    2.17
    că
    2.17
    CPR
    2.15
    daftar
    2.13
    独自
    2.13
     współpr
    2.11
     Cyr
    2.08
    Activations Density 0.000%

    No Known Activations