© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48636
    Prev
    Next
    INDEX
    Explanations

    parking and car rental

    np_acts-logits-general · gemini-2.5-flash-lite

    drugs, attacks, or active

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    <0x0D>
    0.46
     Heroes
    0.44
     Letter
    0.44
     with
    0.43
     Share
    0.43
    ;
    0.43
     Saint
    0.43
     Commissioner
    0.41
     months
    0.41
     DNA
    0.40
    POSITIVE LOGITS
    Benzyloxy
    0.54
    炁
    0.49
     überall
    0.49
    <unused96>
    0.49
     kontinuier
    0.48
    MaxIntensity
    0.47
    ੴ
    0.47
    isierte
    0.47
    зде
    0.46
     toolPath
    0.46
    Activations Density 0.001%

    No Known Activations