© 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. 64716
    Prev
    Next
    INDEX
    Explanations

    classic and learning

    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
     reagents
    0.55
    فو
    0.47
     bowel
    0.45
     Schwartz
    0.45
    న
    0.44
    ަމ
    0.43
     journalists
    0.42
     individual
    0.42
     depth
    0.41
     biosolids
    0.41
    POSITIVE LOGITS
    міні
    0.54
    か
    0.49
     जिनमें
    0.48
    стами
    0.47
     જેમાં
    0.46
     સફેદ
    0.46
    ѡ
    0.44
    trimenti
    0.44
    ⣤
    0.44
    द्योगिक
    0.44
    Activations Density 0.029%

    No Known Activations