© 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. 37457
    Prev
    Next
    INDEX
    Explanations

    while the, purple velvet, vicious KO

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

    requiring specific configurations

    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
    ת
    0.43
     బా
    0.43
     searchObject
    0.42
    рино
    0.41
     contradict
    0.40
     tantos
    0.40
     evapor
    0.40
     convert
    0.40
    াই
    0.40
     chinese
    0.40
    POSITIVE LOGITS
     भोले
    0.46
    landscape
    0.46
    gefühl
    0.46
    iamy
    0.45
    诙
    0.43
    étale
    0.43
    褛
    0.43
     شاعر
    0.43
     Stellung
    0.43
    ですが
    0.42
    Activations Density 0.000%

    No Known Activations