© 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. 22-GEMMASCOPE-RES-131K
    7. 130002
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on “metadata‐style” keywords—words that label or describe structural or descriptive attributes (e.g. metadata, android:background, derive, characterized).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    declarations or structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     standout
    -1.25
     sollten
    -1.22
    Tembelea
    -1.20
    吐槽
    -1.18
    are
    -1.18
     "(
    -1.16
     definite
    -1.15
    裥
    -1.14
    ͛
    -1.13
     reconnaître
    -1.12
    POSITIVE LOGITS
    whereas
    1.16
    Después
    1.16
     vanlig
    1.10
    ophageal
    1.06
     comentarios
    1.05
    тири
    1.03
    CCIÓN
    1.02
     рослин
    1.01
     Manch
    1.01
     nossos
    1.01
    Activations Density 0.000%

    No Known Activations