© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57587
    Prev
    Next
    INDEX
    Explanations

    publication types

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

    The neuron flags genre or section labels in academic and news writing (e.g. “Brief Communication,” “Comment,” “Perspective,” “Symposium,” 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
     না
    -1.17
    entlich
    -1.13
    longitude
    -1.11
    IORITY
    -1.11
    Very
    -1.09
    Information
    -1.06
    ibrill
    -1.06
    ActionCreators
    -1.05
    hojas
    -1.05
     /^
    -1.05
    POSITIVE LOGITS
     about
    1.21
    fonction
    1.20
    жность
    1.18
     этого
    1.15
    ここで
    1.13
    жности
    1.12
    بعد
    1.10
     новый
    1.09
    houettes
    1.09
    位置
    1.08
    Activations Density 0.091%

    No Known Activations