© 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. 76809
    Prev
    Next
    INDEX
    Explanations

    hard and be forgiven

    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
     蛋糕
    -0.75
     Tej
    -0.73
    нта
    -0.70
     Uncertainty
    -0.68
     Jew
    -0.68
    springen
    -0.68
    や
    -0.68
    ĩnh
    -0.68
     xí
    -0.67
    STRUCTURE
    -0.67
    POSITIVE LOGITS
     hard
    3.03
     pressed
    2.39
    hard
    2.25
    pressed
    2.13
    Hard
    1.91
     Pressed
    1.84
     Hard
    1.80
    Pressed
    1.76
    HARD
    1.66
    ハード
    1.51
    Activations Density 0.042%

    No Known Activations