© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14730
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and budget ranges

    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
    ingos
    2.85
    yth
    2.71
    ో
    2.65
    ㈤
    2.62
    етра
    2.54
    т
    2.53
    ే
    2.51
    ्स
    2.49
    ្នែក
    2.48
    ्च
    2.44
    POSITIVE LOGITS
     displaystyle
    2.58
    RTC
    2.36
    ng
    2.35
    धन
    2.33
    cke
    2.27
    ca
    2.26
    జు
    2.26
    ce
    2.23
    ngx
    2.22
    ں
    2.21
    Activations Density 0.009%

    No Known Activations