© 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. 15015
    Prev
    Next
    INDEX
    Explanations

    residences with descriptors

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

    home/apartment/man/professional with

    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
     njegove
    0.45
     jeweiligen
    0.44
     jeweil
    0.42
     продав
    0.42
    诸多
    0.42
    账
    0.42
     메소
    0.41
     цене
    0.41
     тариф
    0.41
     исход
    0.40
    POSITIVE LOGITS
     with
    0.55
     în
    0.54
     فى
    0.47
     in
    0.47
     với
    0.46
    inac
    0.44
     avec
    0.43
     katika
    0.41
     በ
    0.41
     WITH
    0.41
    Activations Density 0.031%

    No Known Activations