© 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. 48692
    Prev
    Next
    INDEX
    Explanations

    when explicitly, without being

    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
    ">(</
    0.54
     titleImageUrl
    0.50
    ാരണ
    0.48
    motiv
    0.48
    ⴹ
    0.47
    Ни
    0.46
     discut
    0.46
    𐰴
    0.46
    𐱅
    0.45
    轫
    0.45
    POSITIVE LOGITS
     parish
    0.45
     Conf
    0.43
    vcxproj
    0.42
    anzia
    0.41
     invaluable
    0.40
     subdivided
    0.39
     subordinate
    0.39
     supervisory
    0.39
     mathematically
    0.38
     Mathematics
    0.38
    Activations Density 0.007%

    No Known Activations