© 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. 160928
    Prev
    Next
    INDEX
    Explanations

    gift box

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

    ominous, massacre, recurring, efficient

    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
     renin
    0.50
     ऑलरेडी
    0.47
    主人公
    0.47
    estis
    0.46
    ム
    0.46
    olisme
    0.45
    జ
    0.45
    檗
    0.45
     মাহবুব
    0.45
    Stdout
    0.44
    POSITIVE LOGITS
     Matric
    0.49
     Phil
    0.47
    ECT
    0.46
     clase
    0.46
     Maid
    0.46
     phil
    0.46
     everlasting
    0.45
     粉
    0.44
    IFT
    0.43
     PHY
    0.43
    Activations Density 0.000%

    No Known Activations