© 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. 64301
    Prev
    Next
    INDEX
    Explanations

    safety guidelines and access restrictions

    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
    ↵
    0.50
     Snapchat
    0.48
     Th
    0.47
    ↵↵
    0.47
     plenty
    0.46
     is
    0.46
     t
    0.45
    i
    0.44
     s
    0.44
     Google
    0.44
    POSITIVE LOGITS
    ურთიერთ
    0.49
    𝖐
    0.46
     зміню
    0.45
     인간
    0.44
     엄마
    0.44
     eccles
    0.44
    女
    0.44
     означа
    0.44
     মম
    0.44
     auxqu
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.