© 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. 109583
    Prev
    Next
    INDEX
    Explanations

    fear or being afraid

    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
    𝑷
    -0.82
     Pali
    -0.78
    Lies
    -0.75
    Ỳ
    -0.73
    フォル
    -0.72
     Scramble
    -0.71
    PRIVACY
    -0.71
     Hints
    -0.70
    吓
    -0.69
    Scooby
    -0.69
    POSITIVE LOGITS
     afraid
    4.09
    怕
    2.58
    fraid
    2.31
     Afraid
    2.17
     miedo
    2.03
     fear
    1.98
     paura
    1.73
     takut
    1.70
     Fear
    1.67
     боя
    1.64
    Activations Density 0.021%

    No Known Activations