© 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. 101062
    Prev
    Next
    INDEX
    Explanations

    lographic structure, studies, direction

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

    The neuron fires on descriptive modifiers—i.e. adjectives and adverbs used to qualify or characterize things.

    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
    le
    -2.81
    o
    -2.48
    to
    -2.42
    h
    -2.41
    ad
    -2.39
    ung
    -2.38
    pa
    -2.33
    ub
    -2.30
    b
    -2.27
    pe
    -2.25
    POSITIVE LOGITS
     Terkait
    2.34
    ן
    2.17
    昔の
    2.08
     rũ
    2.05
    ↵
    2.05
    椹
    2.03
    pfen
    2.02
    chiato
    2.00
     nhưng
    1.99
    alions
    1.97
    Activations Density 0.001%

    No Known Activations