© 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. 14208
    Prev
    Next
    INDEX
    Explanations

    Abuse and

    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
     ;,
    1.67
     xī
    1.66
     Imag
    1.64
     西
    1.57
    Imag
    1.55
     caster
    1.51
     海
    1.48
    渤
    1.45
     Сим
    1.45
     岩
    1.45
    POSITIVE LOGITS
    ঘন
    1.33
     rekan
    1.20
     kompet
    1.16
     sebanyak
    1.15
    ukan
    1.14
    লেট
    1.13
    pesar
    1.12
    পত্রের
    1.10
    penas
    1.10
     nomor
    1.09
    Activations Density 0.033%

    No Known Activations