© 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. 31-GEMMASCOPE-2-RES-65K
    7. 56495
    Prev
    Next
    INDEX
    Explanations

    git commands

    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_65k_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
    /
    0.63
    el
    0.50
     and
    0.49
     E
    0.47
     کی۔
    0.44
    ing
    0.44
     b
    0.43
     or
    0.42
     featuring
    0.42
    es
    0.41
    POSITIVE LOGITS
    parvec
    0.48
    TextMessage
    0.48
    Đây
    0.46
    푦
    0.44
    مر
    0.43
    День
    0.43
    Tidak
    0.43
    Clientes
    0.43
    Texto
    0.42
     उपराष्ट्रपति
    0.42
    Activations Density 0.062%

    No Known Activations