© 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. 127050
    Prev
    Next
    INDEX
    Explanations

    Conditional phrases and instructions

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

    bits, bricks, and ribs

    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
     rejuvenate
    0.57
     subdue
    0.49
     wrinkled
    0.48
    の高い
    0.47
     mouse
    0.46
     trái
    0.45
     minuscule
    0.45
    ∗</
    0.44
     chock
    0.44
     თვით
    0.44
    POSITIVE LOGITS
    1
    0.63
     Allows
    0.58
    name
    0.51
     Completion
    0.51
     Started
    0.51
     Track
    0.49
     Descriptions
    0.49
    origines
    0.49
     First
    0.48
     Requ
    0.48
    Activations Density 0.000%

    No Known Activations