© 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. 18398
    Prev
    Next
    INDEX
    Explanations

    address, postcode, or geographical location

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

    convinced he, faster drying, apologize for

    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
    Transaksi
    0.59
    Enviar
    0.47
    เสนอ
    0.46
    Entities
    0.46
     વ્યક્તિ
    0.46
    🤌
    0.46
     ентите
    0.45
    Collegamenti
    0.45
    ų
    0.45
    ctx
    0.44
    POSITIVE LOGITS
    르면
    0.49
     isl
    0.48
     School
    0.46
     vier
    0.44
     pathogenesis
    0.43
     tiger
    0.43
     rooft
    0.43
     powder
    0.42
     luisant
    0.42
     jefe
    0.42
    Activations Density 0.000%

    No Known Activations