© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58363
    Prev
    Next
    INDEX
    Explanations

    energy and spiritual power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*"
    -0.85
    ⁃
    -0.85
    Véxase
    -0.81
    Recharge
    -0.78
     قاد
    -0.75
    Advisory
    -0.75
     canon
    -0.75
    ător
    -0.75
    ᾽
    -0.75
    immune
    -0.74
    POSITIVE LOGITS
     energy
    3.06
     power
    1.98
     mana
    1.85
     energies
    1.82
    energy
    1.80
     spiritual
    1.66
    énergie
    1.55
     Energy
    1.53
    Energy
    1.53
     énergie
    1.52
    Activations Density 0.014%

    No Known Activations