© 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. 107117
    Prev
    Next
    INDEX
    Explanations

    potential home buyer

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

    contrasting information or qualifications

    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
     utilizando
    0.48
    android
    0.48
    ul
    0.47
     GPS
    0.47
     sentado
    0.46
    p
    0.46
    end
    0.45
    endrá
    0.44
    smartphone
    0.44
    ólogos
    0.44
    POSITIVE LOGITS
    ‍या
    0.44
    Эти
    0.44
    Ф
    0.44
    și
    0.43
    клары
    0.42
    педия
    0.42
     జీవిత
    0.42
    azioni
    0.42
     வாழ்க்க
    0.41
    chanics
    0.41
    Activations Density 0.000%

    No Known Activations