© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120264
    Prev
    Next
    INDEX
    Explanations

    worn objects and attire

    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_40_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
    樯
    0.44
     filas
    0.43
    pads
    0.43
     প্রান্ত
    0.41
    Filename
    0.41
     fillets
    0.41
     आस
    0.40
    泰国
    0.39
     puertos
    0.39
    낑
    0.39
    POSITIVE LOGITS
     gold
    0.61
     spectacles
    0.58
     silver
    0.56
     leather
    0.56
     ring
    0.55
     sword
    0.54
     book
    0.51
     knife
    0.51
     boots
    0.50
     pistols
    0.49
    Activations Density 0.016%

    No Known Activations