© 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. 10-GEMMASCOPE-RES-131K
    7. 44755
    Prev
    Next
    INDEX
    Explanations

    version numbers and compiler versions

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

    The neuron flags version‐related identifiers (e.g. “_MSC_VER,” “version,” “version_info,” 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
    d
    -1.90
    f
    -1.76
    k
    -1.65
    r
    -1.61
     ști
    -1.55
    t
    -1.55
     serão
    -1.52
    似的
    -1.49
    𝐛
    -1.47
     with
    -1.45
    POSITIVE LOGITS
    Warum
    1.83
     surpren
    1.76
    Deine
    1.73
    Jetzt
    1.72
    Noch
    1.69
     empfohlen
    1.67
    ویژگی
    1.63
    Nicht
    1.60
    Neben
    1.58
     Problemen
    1.58
    Activations Density 0.001%

    No Known Activations