© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8123
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    煐
    0.36
    颛
    0.34
    驷
    0.32
    ของการ
    0.31
     변화
    0.30
     반복
    0.30
     효과
    0.30
    ᕇ
    0.29
    强调
    0.29
     అధికారు
    0.29
    POSITIVE LOGITS
     cities
    0.56
     cidades
    0.56
     مدينة
    0.56
     cidade
    0.53
     London
    0.52
     città
    0.49
    مدينة
    0.49
     ciudades
    0.49
     ciudad
    0.48
     miasta
    0.47
    Activations Density 0.070%

    No Known Activations