© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35992
    Prev
    Next
    INDEX
    Explanations

    around the world

    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
     internacionales
    0.58
     globales
    0.58
    erde
    0.55
     міжнарод
    0.55
    ن
    0.55
    全球
    0.54
     дав
    0.53
    international
    0.53
     económicos
    0.53
     internationales
    0.52
    POSITIVE LOGITS
     in
    0.55
     t
    0.54
    ்துற
    0.51
     kulit
    0.50
    กับ
    0.50
     existing
    0.48
     njeg
    0.46
     kanssa
    0.46
     whose
    0.45
     people
    0.45
    Activations Density 0.013%

    No Known Activations