© 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. 10-GEMMASCOPE-RES-131K
    7. 128005
    Prev
    Next
    INDEX
    Explanations

    immutable

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

    The neuron responds to occurrences of the words “immutable” or “mutable” (and their variants).

    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
     antics
    -2.83
    actéristi
    -2.78
    縢
    -2.75
     unn
    -2.59
     terrific
    -2.45
     glimpses
    -2.44
     quintessential
    -2.44
     hapless
    -2.41
     delightfully
    -2.39
     depictions
    -2.39
    POSITIVE LOGITS
    there
    2.73
     seems
    2.64
    just
    2.61
     suggests
    2.52
    when
    2.52
    𝟮
    2.48
     requires
    2.47
     noteworthy
    2.44
     removes
    2.42
     solely
    2.38
    Activations Density 0.003%

    No Known Activations