© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92032
    Prev
    Next
    INDEX
    Explanations

    hypnosis and suggestion

    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
     ORGAN
    -0.76
     kitchenette
    -0.75
    werte
    -0.74
    ologique
    -0.73
     Mobility
    -0.73
     Hedgehog
    -0.71
     sociology
    -0.70
     bleached
    -0.70
     electrocardio
    -0.69
     Gry
    -0.69
    POSITIVE LOGITS
     hypno
    1.95
     hypnosis
    1.88
     hyp
    1.84
     Hyp
    1.70
     hypnotic
    1.61
     suggestion
    1.51
     suggestions
    1.50
    suggestion
    1.45
     sugges
    1.40
    Hyp
    1.30
    Activations Density 0.018%

    No Known Activations