© 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. 20247
    Prev
    Next
    INDEX
    Explanations

    that privacy

    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
     Facultad
    0.48
    ל
    0.47
     металла
    0.47
    د
    0.46
     HOWEVER
    0.45
    жні
    0.44
    㡷
    0.43
    )<
    0.42
    言い
    0.42
    금
    0.41
    POSITIVE LOGITS
     असलेल्या
    0.47
    analog
    0.45
     Pitch
    0.45
    row
    0.44
     systems
    0.44
     stor
    0.43
     给
    0.43
    ocycl
    0.42
    pitch
    0.42
     nest
    0.42
    Activations Density 0.021%

    No Known Activations