© 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. 10-GEMMASCOPE-RES-131K
    4. 9819
    Prev
    Next
    INDEX
    Explanations

    showing or offering

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

    The neuron strongly activates on evaluative or critical phrasing—especially review-style action verbs and related nouns (e.g. “depicts,” “shows,” “argues,” “offers,” “reveals,” “establishes,” “allows insight,” etc.).

    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
     when
    -2.00
     for
    -1.63
     by
    -1.61
     can
    -1.49
     these
    -1.45
    when
    -1.41
     because
    -1.34
     cuando
    -1.27
     pudieron
    -1.25
     our
    -1.24
    POSITIVE LOGITS
     dente
    1.48
    lateinit
    1.42
     agres
    1.41
    despite
    1.36
     vant
    1.32
     poulet
    1.31
    committed
    1.31
     persil
    1.30
    quelles
    1.30
     THIRD
    1.30
    Activations Density 0.120%

    No Known Activations