© 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. 8707
    Prev
    Next
    INDEX
    Explanations

    variable assignments

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

    The neuron is looking for debugging output calls (e.g. print or log statements and their string‐literal arguments).

    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
     If
    -2.14
     Ако
    -1.73
     will
    -1.73
     Чтобы
    -1.67
     Unlike
    -1.66
     Ihr
    -1.65
     These
    -1.63
     mengunjungi
    -1.63
     Each
    -1.63
     Unless
    -1.59
    POSITIVE LOGITS
     they
    1.89
    }$.
    1.69
    swire
    1.64
     industrie
    1.59
    itisation
    1.58
    itación
    1.54
    }
    1.54
    趵
    1.52
    ulitis
    1.52
    lograph
    1.52
    Activations Density 0.004%

    No Known Activations