© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220548
    Prev
    Next
    INDEX
    Explanations

    energy and catalysis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    мена
    0.43
    Saya
    0.43
     reservas
    0.41
     Drops
    0.41
    algorith
    0.41
     रक्षाबंधनाच्या
    0.40
     सहायता
    0.40
    𝙰
    0.40
     réserve
    0.39
     Saya
    0.39
    POSITIVE LOGITS
     energy
    0.57
     energi
    0.48
     catalyst
    0.46
     Energy
    0.45
     catalyzed
    0.45
    エネルギー
    0.43
     에너지
    0.42
     enerji
    0.42
     energética
    0.41
    Energy
    0.41
    Activations Density 0.001%

    No Known Activations