© 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. 134662
    Prev
    Next
    INDEX
    Explanations

    free/rent related phrasing

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

    keyword, friends, and depending on context

    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
    ום
    0.50
     userAnswer
    0.48
    ௌ
    0.47
    ்களை
    0.47
    ości
    0.47
    getSeconds
    0.47
    ം
    0.47
    щей
    0.46
    亽
    0.46
    יים
    0.46
    POSITIVE LOGITS
     restaurant
    0.51
     reforestation
    0.49
     kindergarten
    0.47
     rented
    0.46
     Kroger
    0.45
     reh
    0.45
     Christensen
    0.45
     Costco
    0.45
     retails
    0.45
     wobble
    0.44
    Activations Density 0.001%

    No Known Activations