© 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. 14529
    Prev
    Next
    INDEX
    Explanations

    Solar, min, mobile, infra

    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
    e
    3.08
    t
    3.03
    tion
    2.84
    tio
    2.80
    elem
    2.80
    ture
    2.79
    tive
    2.74
    ead
    2.63
    ei
    2.58
    ी
    2.58
    POSITIVE LOGITS
    ٹرول
    2.51
    年モデル
    2.31
    ibilities
    2.31
    uari
    2.20
    ｋ
    2.19
    ্ম্ম
    2.19
    enames
    2.18
    ږ
    2.18
    
    2.17
    াগর
    2.16
    Activations Density 0.006%

    No Known Activations