© 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. 32086
    Prev
    Next
    INDEX
    Explanations

    money, copyright, names, abbreviations

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

    safety and regulations

    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
    Scenario
    0.45
    ዓ
    0.45
    Cartoon
    0.44
    Creation
    0.43
    Creator
    0.42
    Contributor
    0.42
     Creation
    0.42
    鬃
    0.42
     Environments
    0.41
    Allow
    0.40
    POSITIVE LOGITS
    \$
    0.42
     \$
    0.41
     vaya
    0.40
    ！？
    0.38
     prakt
    0.38
     願い
    0.38
     nata
    0.38
     【
    0.38
     nahi
    0.38
     practical
    0.38
    Activations Density 0.003%

    No Known Activations