© 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. 12919
    Prev
    Next
    INDEX
    Explanations

    POST request

    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
    นาง
    2.44
    multirow
    2.27
    вает
    2.24
    此之外
    2.22
    了
    2.21
    ková
    2.18
    ლ
    2.18
    productions
    2.15
    اً
    2.15
    table
    2.07
    POSITIVE LOGITS
     pp
    2.17
    ers
    1.85
     cir
    1.84
     ste
    1.83
    aruh
    1.82
     na
    1.81
     ble
    1.80
     sl
    1.79
    .(
    1.78
    ceedings
    1.78
    Activations Density 0.043%

    No Known Activations