© 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. 14357
    Prev
    Next
    INDEX
    Explanations

    replace with similar

    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
    aternary
    2.59
    qiya
    2.56
    ibalsan
    2.46
    ब्दिक
    2.45
    ellular
    2.45
     idling
    2.43
    َنْ
    2.41
    icating
    2.39
    дня
    2.38
    ｋ
    2.35
    POSITIVE LOGITS
    php
    3.33
    üşt
    3.17
    ంటి
    2.61
    Gur
    2.52
    ার্জ
    2.50
    GON
    2.48
     congruent
    2.45
    GISL
    2.44
    PARAMS
    2.43
    перед
    2.43
    Activations Density 0.026%

    No Known Activations