© 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. 22-GEMMASCOPE-RES-131K
    7. 72069
    Prev
    Next
    INDEX
    Explanations

    words that include

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

    The neuron is sharply tuned to detecting “non-volatile memory”(and closely related memory-type) terminology in technical descriptions of computer memory.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    女士
    -0.92
    creva
    -0.87
     ambos
    -0.82
     when
    -0.82
     beide
    -0.81
     cairan
    -0.81
     rune
    -0.81
     atenta
    -0.81
    COLON
    -0.80
     stuks
    -0.80
    POSITIVE LOGITS
     include
    1.89
     includes
    1.56
     gồm
    1.54
    分别是
    1.45
    Includes
    1.42
     comprises
    1.30
     meliputi
    1.27
     namely
    1.26
     among
    1.25
    Examples
    1.25
    Activations Density 0.174%

    No Known Activations