© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198536
    Prev
    Next
    INDEX
    Explanations

    No shame here!

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining abstract concepts and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.45
    Severity
    0.44
    欹
    0.44
    Vision
    0.41
    Scientific
    0.41
    난
    0.41
    IGN
    0.40
    вів
    0.40
    ||
    0.39
    
    0.39
    POSITIVE LOGITS
     جوړونکی
    0.53
    انوں
    0.52
    iciable
    0.50
     physiologically
    0.48
     agua
    0.48
    rscheinlich
    0.47
     catchy
    0.47
     ChAT
    0.45
     hefyd
    0.45
    ẏ
    0.45
    Activations Density 0.000%

    No Known Activations