© 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. 22-GEMMASCOPE-RES-131K
    7. 35116
    Prev
    Next
    INDEX
    Explanations

    subtle hints and clues

    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_22/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
     beteken
    -0.97
    嘣
    -0.90
     BLANK
    -0.90
     hoge
    -0.88
     perfecte
    -0.86
    얘
    -0.86
    起了
    -0.84
    ENSEN
    -0.84
     柜
    -0.83
    Évaluation
    -0.83
    POSITIVE LOGITS
     clues
    1.66
     information
    1.43
     hidden
    1.34
     subtle
    1.31
     opportunities
    1.28
     subtly
    1.25
     every
    1.23
     hints
    1.23
     each
    1.12
     tools
    1.08
    Activations Density 0.071%

    No Known Activations