© 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. 37887
    Prev
    Next
    INDEX
    Explanations

    negative self-talk

    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
     notched
    -0.95
    しくは
    -0.95
     congratulated
    -0.92
    ázka
    -0.87
     daß
    -0.86
    颊
    -0.84
    Pada
    -0.84
    Atentamente
    -0.83
    lapsible
    -0.83
    inoma
    -0.83
    POSITIVE LOGITS
     Negative
    1.70
    Negative
    1.64
     negative
    1.45
    negative
    1.28
     NEGATIVE
    1.22
     consequences
    1.20
     (-)
    1.20
    NEGATIVE
    1.11
     publicity
    1.04
     connotations
    1.03
    Activations Density 0.014%

    No Known Activations