© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 219897
    Prev
    Next
    INDEX
    Explanations

    mystical energies and secret identities

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Superman
    0.87
    Superman
    0.85
     Avengers
    0.84
     Batman
    0.82
     batman
    0.81
     Marvel
    0.79
    Batman
    0.77
    Avengers
    0.76
    Marvel
    0.74
    🦸
    0.73
    POSITIVE LOGITS
    蘅
    0.42
     Phosph
    0.41
    White
    0.40
    ốt
    0.40
     যৌন
    0.40
    Costa
    0.40
    Configuration
    0.40
     receiving
    0.39
     Vietnam
    0.39
    killer
    0.39
    Activations Density 0.014%

    No Known Activations