© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32775
    Prev
    Next
    INDEX
    Explanations

    fit any

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

    The neuron fires on strong, promotional action verbs that describe a product’s ability or capacity to meet needs or requirements.

    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
     Some
    -1.63
     after
    -1.58
     there
    -1.48
     by
    -1.44
     некоторые
    -1.42
     it
    -1.41
     using
    -1.41
     attempting
    -1.41
     if
    -1.40
     when
    -1.40
    POSITIVE LOGITS
     any
    3.31
     cualquier
    3.13
    任何
    2.97
     både
    2.89
    どんな
    2.89
     qualsiasi
    2.88
     qualquer
    2.83
     ANY
    2.72
     любой
    2.48
     любого
    2.42
    Activations Density 0.097%

    No Known Activations