© 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. 14368
    Prev
    Next
    INDEX
    Explanations

    mathematical structured definitions

    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
     ⋮
    2.36
    рованного
    2.29
    рованный
    2.23
    Ꮶ
    2.20
     représ
    2.17
    рованные
    2.14
    рованных
    2.09
    рованное
    2.08
    SHARE
    2.07
     représentent
    2.07
    POSITIVE LOGITS
    URIS
    1.90
    ur
    1.89
    lte
    1.79
    uve
    1.73
    œ
    1.72
    地
    1.66
    ure
    1.64
    थ
    1.59
     obvi
    1.57
    oraus
    1.55
    Activations Density 0.057%

    No Known Activations