© 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. 14304
    Prev
    Next
    INDEX
    Explanations

    enough water

    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
    𝐚
    2.82
    𝐞
    2.57
    zeich
    2.50
    an
    2.38
    zni
    2.38
    𝐠
    2.36
    ಗಳು
    2.35
    𝐤
    2.23
    𝐡
    2.23
    ování
    2.19
    POSITIVE LOGITS
    s
    3.33
    িপি
    2.84
    」「
    2.82
    tics
    2.80
    ses
    2.78
    ات
    2.76
    ๅ
    2.59
    sed
    2.58
    sen
    2.57
    sene
    2.51
    Activations Density 0.010%

    No Known Activations