© 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. 10-GEMMASCOPE-RES-131K
    7. 129701
    Prev
    Next
    INDEX
    Explanations

    hint or tip

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates strongly on section‐heading labels like “Tip:”, “Hint:”, “Beauty tip:”, etc., i.e. lines introducing tips or hints.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     químicas
    -1.46
    "",
    -1.41
    獃
    -1.37
     slecht
    -1.34
    )&&(
    -1.34
    ledad
    -1.34
     huset
    -1.32
     gydy
    -1.29
    贗
    -1.28
    boneca
    -1.27
    POSITIVE LOGITS
     by
    2.17
     if
    2.13
     anklicken
    1.53
    nachron
    1.49
     weren
    1.45
    you
    1.35
     where
    1.34
     contrario
    1.33
     shouldn
    1.31
     think
    1.30
    Activations Density 0.008%

    No Known Activations