© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10617
    Prev
    Next
    INDEX
    Explanations

    code closing syntax

    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
     aves
    2.24
    MEAN
    2.23
    annan
    2.20
     Etihad
    2.19
     Boiler
    2.18
    ](./
    2.18
    EXEC
    2.16
    HPV
    2.10
    ूण
    2.10
     "]
    2.10
    POSITIVE LOGITS
    ního
    1.99
    zī
    1.95
    দ্ম
    1.93
    きの
    1.89
     northern
    1.85
    fed
    1.84
     اتارنا
    1.84
    issimus
    1.83
     dönd
    1.82
    tains
    1.81
    Activations Density 0.006%

    No Known Activations