© 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. 201351
    Prev
    Next
    INDEX
    Explanations

    Certain, Warm, Thank, Selected

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

    package definition

    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
    aliana
    0.52
     시작
    0.48
    кої
    0.47
     Philly
    0.47
    ovíd
    0.47
     Francisco
    0.47
    кій
    0.46
    ఘ
    0.46
     Lire
    0.45
    žky
    0.45
    POSITIVE LOGITS
     remnant
    0.42
     endangering
    0.42
    тный
    0.40
     הע
    0.39
    Runnable
    0.38
    ധ്യ
    0.38
     техни
    0.38
     relic
    0.38
     tendrás
    0.38
    এব
    0.38
    Activations Density 0.002%

    No Known Activations