© 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. 16-GEMMASCOPE-2-RES-262K
    7. 141670
    Prev
    Next
    INDEX
    Explanations

    Bose or Sega consoles

    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_16_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
     on
    1.02
    ن
    0.95
     a
    0.81
    on
    0.73
    ق
    0.70
    1
    0.68
    ح
    0.67
     as
    0.67
    كا
    0.66
     ON
    0.66
    POSITIVE LOGITS
    ="
    0.73
    ်
    0.68
    0.64
    lasti
    0.62
    寜
    0.59
    L
    0.57
     счета
    0.55
    ാ
    0.55
    ನ್
    0.55
    劑
    0.55
    Activations Density 0.003%

    No Known Activations