© 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. 56408
    Prev
    Next
    INDEX
    Explanations

    file sharing and illegal activities

    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
     be
    0.44
     red
    0.39
    :
    0.39
     aromatic
    0.38
     blood
    0.38
     con
    0.37
     lumen
    0.37
    N
    0.37
    V
    0.37
     component
    0.37
    POSITIVE LOGITS
    aliśmy
    0.49
     счастли
    0.46
     финансо
    0.46
     financières
    0.45
    ႃႇ
    0.44
    结婚
    0.43
     금융
    0.42
    addena
    0.42
     również
    0.42
    赚钱
    0.42
    Activations Density 0.000%

    No Known Activations