© 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. 13034
    Prev
    Next
    INDEX
    Explanations

    чем закончился

    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
    ut
    2.23
    ็น
    2.16
    utlich
    2.15
    as
    2.12
    baw
    2.03
    𝐜
    2.02
    cur
    2.02
    rological
    1.98
    वंशी
    1.95
    뿜
    1.95
    POSITIVE LOGITS
    evan
    2.96
     Autres
    2.53
     planks
    2.45
     carbides
    2.38
     impuesto
    2.37
    剩下
    2.37
     clearances
    2.34
    ubility
    2.34
     untreated
    2.33
    жив
    2.29
    Activations Density 0.000%

    No Known Activations