© 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. 115997
    Prev
    Next
    INDEX
    Explanations

    international success

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

    respectful discussion of sensitive topics

    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
    etailed
    0.45
    两者
    0.45
    那时
    0.43
    眼
    0.43
    olisme
    0.42
     уме
    0.41
     pored
    0.41
    leza
    0.41
    j
    0.41
     Росії
    0.40
    POSITIVE LOGITS
    AlertType
    0.48
    herokuapp
    0.48
     nėra
    0.47
     Debut
    0.45
     নেওয়া
    0.45
    ای
    0.42
    সমা
    0.42
     diventa
    0.42
     nebude
    0.41
     vendido
    0.41
    Activations Density 0.000%

    No Known Activations