© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    official resources and documentation

    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
    ujacy
    1.90
    <unused768>
    1.79
    gameObjects
    1.78
    bolos
    1.74
    nyez
    1.73
    pyridazine
    1.72
    dincer
    1.68
    striées
    1.68
    codewords
    1.67
    ayvachi
    1.67
    POSITIVE LOGITS
     Ryan
    1.32
     our
    1.31
     or
    1.22
     Al
    1.20
     F
    1.20
     Our
    1.19
    c
    1.19
     Arm
    1.17
     Cal
    1.17
     Michael
    1.16
    Activations Density 0.577%

    No Known Activations