© 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. 14249
    Prev
    Next
    INDEX
    Explanations

    bash script shebang

    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
    ា
    2.97
    㳳
    2.78
    า
    2.77
     конца
    2.73
    erView
    2.69
    oje
    2.64
    㸵
    2.60
    ⟤
    2.60
    JSPA
    2.60
    atosis
    2.59
    POSITIVE LOGITS
    self
    2.28
    sel
    2.07
    세
    2.05
    Oréal
    1.93
    붙
    1.91
    th
    1.88
    www
    1.88
    spend
    1.84
     પુર
    1.83
    sl
    1.82
    Activations Density 0.001%

    No Known Activations