© 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. 73215
    Prev
    Next
    INDEX
    Explanations

    mechanistic, experiential, descriptive, exploratory

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

    The neuron fires on long, formal academic adjectives or methodological descriptors (e.g. interpretative, mechanistic, probabilistic, evidentiary, experiential).

    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
    }
    -1.44
     individuellen
    -1.41
    tées
    -1.38
    ྥ
    -1.37
     vollständ
    -1.37
    VIATIONS
    -1.35
     принад
    -1.32
    浮现
    -1.31
     Gefühl
    -1.28
     ทั้ง
    -1.27
    POSITIVE LOGITS
    としての
    1.55
    против
    1.39
    和我
    1.36
    :'#
    1.36
    diario
    1.35
    全是
    1.34
    ताओं
    1.34
     oriented
    1.34
    gne
    1.33
    ではまた
    1.32
    Activations Density 0.070%

    No Known Activations