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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2274
    Prev
    Next
    INDEX
    Explanations

    brew install commands

    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
    ®
    2.08
    ’
    2.07
    ™
    1.81
     tarafından
    1.71
    '
    1.71
     famoso
    1.55
     Speaks
    1.54
     menyediakan
    1.54
     menyebut
    1.53
     lainnya
    1.50
    POSITIVE LOGITS
    <unused298>
    1.81
    <unused958>
    1.69
    <unused747>
    1.69
    <unused768>
    1.66
    <unused1252>
    1.63
    <unused742>
    1.63
     disruptive
    1.63
     pptn
    1.62
    <unused921>
    1.60
     coveredmethods
    1.60
    Activations Density 0.273%

    No Known Activations