© 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. 22052
    Prev
    Next
    INDEX
    Explanations

    NVIDIA {GTX/Ti} graphics cards

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

    The neuron fires on GPU hardware model identifiers (brand names plus numeric model codes, e.g., “GTX 560 Ti,” “Radeon HD 6870,” 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
     Krzysz
    -1.53
     pittores
    -1.48
    ⑊
    -1.42
    
    -1.41
     intelligente
    -1.39
     Songtext
    -1.39
     postale
    -1.39
     orientale
    -1.39
     tedesco
    -1.38
     fecond
    -1.38
    POSITIVE LOGITS
     We
    1.31
     now
    1.27
    愧
    1.25
     we
    1.23
     our
    1.21
     more
    1.21
    驭
    1.20
     meestal
    1.20
    怔
    1.16
     so
    1.12
    Activations Density 0.011%

    No Known Activations