© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12425
    Prev
    Next
    INDEX
    Explanations

    relaxation and comfort

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

    cozy relaxation

    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
    reports
    0.42
    participant
    0.42
    लेट्स
    0.41
    ncol
    0.41
    objective
    0.40
    谒
    0.40
    DAILY
    0.40
    button
    0.39
    acid
    0.39
    cimientos
    0.39
    POSITIVE LOGITS
     relaxing
    1.05
     lounging
    1.05
     relax
    0.98
     relaxation
    0.93
     lounge
    0.93
     gemüt
    0.91
     Relaxation
    0.89
     Relax
    0.88
    惬
    0.87
    Relax
    0.86
    Activations Density 0.140%

    No Known Activations