© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89956
    Prev
    Next
    INDEX
    Explanations

    specific programming terms

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

    The neuron fires on Scala generic‐type parameter lists and variance annotations (e.g. the “[A, +B, -Z, Y]” brackets and type‐parameter names).

    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
     Klein
    -0.87
    дав
    -0.85
    めの
    -0.83
     thither
    -0.82
     seventies
    -0.78
    Klein
    -0.77
    뜨
    -0.77
    ・)
    -0.74
     those
    -0.73
     as
    -0.73
    POSITIVE LOGITS
     with
    0.91
    ]=
    0.90
     =>
    0.83
     abuelos
    0.82
    ătoare
    0.82
    }}=\
    0.80
    ]#
    0.80
    fortable
    0.79
     tulang
    0.78
    ience
    0.78
    Activations Density 0.010%

    No Known Activations