© 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. 28598
    Prev
    Next
    INDEX
    Explanations

    average price

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

    upfront costs and features

    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
     Romania
    0.63
     India
    0.55
     Indonesia
    0.55
     Hong
    0.54
    0.54
     In
    0.54
    </sub>
    0.53
     This
    0.52
     Ireland
    0.52
     Hawking
    0.50
    POSITIVE LOGITS
    établ
    0.52
    établir
    0.51
     رنز
    0.50
     tumeurs
    0.50
    营收
    0.50
     subpoenas
    0.49
    ल्लाला
    0.49
    สำหรับการ
    0.47
    赁
    0.47
    푅
    0.47
    Activations Density 0.002%

    No Known Activations