© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62826
    Prev
    Next
    INDEX
    Explanations

    LIB interest rates

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

    This neuron detects discourse‐level signposts and enumerative transitions (e.g. “The truth of it is,” “The first factor is,” “For example,” numbered or list-style introductions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    𝔶
    -0.79
     RATIO
    -0.75
     contenedor
    -0.73
    🪥
    -0.73
    ждение
    -0.73
    otus
    -0.72
    moderate
    -0.71
    atify
    -0.71
     ROUTE
    -0.71
     Rasmus
    -0.71
    POSITIVE LOGITS
     LIB
    1.54
     overnight
    1.51
     Overnight
    1.36
     short
    1.34
     Lib
    1.22
     inter
    1.20
    Overnight
    1.17
     Short
    1.16
    Short
    1.12
    LIB
    1.09
    Activations Density 0.020%

    No Known Activations