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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81100
    Prev
    Next
    INDEX
    Explanations

    psychic or clairvoyant

    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
     kites
    -0.72
     Smart
    -0.70
     consuma
    -0.69
     тър
    -0.68
    rawtypes
    -0.68
    érations
    -0.67
    zionato
    -0.67
     mariner
    -0.66
    ajemy
    -0.66
    meyi
    -0.65
    POSITIVE LOGITS
     psychic
    3.11
     Psychic
    2.34
     clair
    2.34
    Psychic
    2.30
     psych
    2.30
    psy
    2.02
     Psych
    1.84
    psych
    1.75
    Psych
    1.71
     PSYCH
    1.69
    Activations Density 0.036%

    No Known Activations