© 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. 100843
    Prev
    Next
    INDEX
    Explanations

    oriented around

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

    compelling descriptions, pushing video, manipulating governments

    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
    誣
    0.50
     trembled
    0.49
     sins
    0.46
     hearers
    0.44
     sufferings
    0.43
     deafness
    0.43
     tormented
    0.43
    爍
    0.43
     blindness
    0.42
     selben
    0.42
    POSITIVE LOGITS
     BBQ
    0.47
    ándo
    0.47
     homeowners
    0.46
     remodel
    0.45
     बच्‍चे
    0.44
    óny
    0.44
     ď
    0.43
     seasonally
    0.43
    ंसह
    0.43
     Seafood
    0.42
    Activations Density 0.001%

    No Known Activations