© 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. 14273
    Prev
    Next
    INDEX
    Explanations

    contend, within

    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
    h
    2.80
    鹂
    2.78
    茴
    2.69
    iad
    2.68
    ਂ
    2.64
    zano
    2.60
    pty
    2.50
    asch
    2.48
     "$(
    2.44
    ᵖ
    2.42
    POSITIVE LOGITS
    াকাছি
    2.73
    buri
    2.69
    […]
    2.69
    ཛ
    2.48
    कारा
    2.47
    heastern
    2.44
    горь
    2.42
    __|
    2.40
     uppermost
    2.36
    ্প্র
    2.35
    Activations Density 0.008%

    No Known Activations