© 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. 22-GEMMASCOPE-RES-131K
    4. 28133
    Prev
    Next
    INDEX
    Explanations

    start of phrases or sentences

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

    The neuron identifies forward‐looking statements or disclaimers about future results and expectations in corporate or financial text.

    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
     from
    -1.57
     even
    -1.26
     by
    -1.26
     every
    -1.16
     so
    -1.09
     like
    -1.05
    ;
    -1.03
     all
    -1.02
     first
    -1.02
     for
    -0.99
    POSITIVE LOGITS
    исленность
    1.32
    OGND
    1.28
    ícias
    1.28
     espesor
    1.23
    obrázek
    1.21
    Ṃ
    1.20
     cierre
    1.19
    いです
    1.17
    があり
    1.16
     rekomendasi
    1.14
    Activations Density 0.003%

    No Known Activations