© 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. 104464
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    physical or emotional limitations

    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
     purpure
    0.46
    .
    0.45
    ।
    0.44
     Champion
    0.44
     regulars
    0.43
     commentaries
    0.43
    ButtonItem
    0.42
     annot
    0.42
     rumours
    0.42
     savoury
    0.42
    POSITIVE LOGITS
    porque
    0.53
     нацыяна
    0.49
    же
    0.47
     защото
    0.47
     riforma
    0.44
    邂
    0.44
     sebagian
    0.44
    ាហ
    0.44
    ieht
    0.42
     गांधी
    0.42
    Activations Density 0.002%

    No Known Activations