© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    NYC, Pittsburgh, or Cairo

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

    parsing Bloomberg, contact AWS, deal with

    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
    
    0.46
     numai
    0.44
     .........
    0.44
     !
    0.44
       
    0.43
    ᆢ
    0.42
     .......
    0.42
    贮
    0.41
     .
    0.41
    樂
    0.41
    POSITIVE LOGITS
    Alongside
    0.68
     impactful
    0.66
     fanbase
    0.66
     LGBTQ
    0.65
     reimag
    0.65
    🫡
    0.64
     alongside
    0.61
    伱
    0.61
     Alongside
    0.61
     synced
    0.61
    Activations Density 0.081%

    No Known Activations