© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    Staking

    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
    lah
    2.18
    ly
    1.92
    th
    1.73
    un
    1.71
    bo
    1.66
    sh
    1.58
    j
    1.55
    seh
    1.54
    unk
    1.49
     un
    1.47
    POSITIVE LOGITS
    <unused1672>
    3.07
     formContext
    3.03
    enamefont
    3.01
    <unused1768>
    3.00
     iccad
    3.00
    <unused1166>
    2.97
    <unused180>
    2.95
    <unused1766>
    2.95
    arrerol
    2.93
     llrp
    2.93
    Activations Density 0.040%

    No Known Activations