© 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. 20681
    Prev
    Next
    INDEX
    Explanations

    specific problem types but

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

    This neuron activates on the word “specific” (especially in contexts like “specific to,” “OS-specific,” 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
    "]=
    -1.16
    danke
    -1.13
     through
    -1.13
    ,\,\
    -1.13
    óis
    -1.10
     oleh
    -1.10
    ukup
    -1.09
    鉴
    -1.09
     caracteres
    -1.08
    狃
    -1.07
    POSITIVE LOGITS
    >
    1.21
    ABOUT
    1.17
    ffichage
    1.16
    }
    1.16
     then
    1.15
     I
    1.14
     escolher
    1.13
    𝕔
    1.13
    About
    1.13
     любы
    1.09
    Activations Density 0.045%

    No Known Activations