© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 108
    Prev
    Next
    INDEX
    Explanations

    biological order suffixes

    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
     NORMAL
    0.89
    fqsen
    0.88
    াহিনী
    0.88
    wpilibj
    0.86
    않
    0.82
    롭게
    0.81
    <unused1237>
    0.80
    <unused1252>
    0.79
    <unused1877>
    0.79
     coveredmethods
    0.79
    POSITIVE LOGITS
     recomiendo
    1.10
    Å
    1.04
    ani
    1.03
    先生
    1.02
    os
    1.02
     Akademi
    1.01
     manio
    1.01
    ula
    1.00
    Ã
    1.00
     আশ্রম
    0.99
    Activations Density 6.284%

    No Known Activations