© 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. 54141
    Prev
    Next
    INDEX
    Explanations

    to know, and Nike, research

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

    temporal modifiers

    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
     strawberry
    0.48
     necklaces
    0.48
     Ä
    0.48
    새
    0.48
     pixie
    0.47
     necklace
    0.43
    Ан
    0.43
    勸
    0.42
     strawberries
    0.42
     symbolName
    0.42
    POSITIVE LOGITS
    inthe
    0.50
    you
    0.49
    ashions
    0.47
     سنج
    0.45
    iling
    0.45
    ينات
    0.45
    ursing
    0.44
    iesen
    0.44
    ethers
    0.44
     ගන්න
    0.44
    Activations Density 0.000%

    No Known Activations