© 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. 14265
    Prev
    Next
    INDEX
    Explanations

    replatforming

    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
    പ
    2.63
    ून्य
    2.61
    cps
    2.47
    ഘാ
    2.43
    輒
    2.42
    訕
    2.37
    teria
    2.37
    ारीरिक
    2.35
    ч
    2.33
    नै
    2.28
    POSITIVE LOGITS
    <bos>
    3.08
    𝙪
    2.47
    фона
    2.29
    oclip
    2.23
    кара
    2.21
    Sent
    2.20
    𝙢
    2.14
     carry
    2.12
     carrying
    2.10
    werden
    2.07
    Activations Density 0.004%

    No Known Activations