© 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. 1044
    Prev
    Next
    INDEX
    Explanations

    Manhattan area, city, symbols, colors

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

    Identity and information categorization

    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
    ，
    0.48
    प
    0.45
     anf
    0.45
    \|^{
    0.44
    ه
    0.44
     malice
    0.44
    د
    0.43
    ד
    0.43
    不愿意
    0.42
    л
    0.42
    POSITIVE LOGITS
     미술
    0.53
     শিল্পী
    0.48
     వెంట
    0.47
     കമ്മി
    0.47
     مساله
    0.47
     магазине
    0.46
    বাধিকার
    0.46
     organisasi
    0.46
    ത്രി
    0.46
     సంగీ
    0.46
    Activations Density 0.000%

    No Known Activations