© 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. 235037
    Prev
    Next
    INDEX
    Explanations

    numbers, prices, disease, delivery

    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
     presenter
    0.53
    頴
    0.51
     साक्षी
    0.50
    हत
    0.49
     kehad
    0.48
     hapl
    0.48
     gadis
    0.48
     zespołu
    0.48
     Danilo
    0.48
     mengatur
    0.47
    POSITIVE LOGITS
    0
    0.50
    seven
    0.43
    -
    0.43
    three
    0.42
    five
    0.42
    EMI
    0.42
    ­
    0.41
    lications
    0.41
    ,
    0.41
    al
    0.40
    Activations Density 0.001%

    No Known Activations