© 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. 22-GEMMASCOPE-RES-131K
    7. 66563
    Prev
    Next
    INDEX
    Explanations

    code and source code files

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

    The neuron fires on programming‐ or software‐related identifiers and keywords (e.g. module/class names, API calls, dropdown/menu tokens, file extensions, function names, 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_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
    y
    -1.19
    w
    -1.08
    no
    -1.02
    ch
    -0.97
     &=
    -0.97
    each
    -0.96
    ra
    -0.94
    rec
    -0.94
    ien
    -0.92
    g
    -0.92
    POSITIVE LOGITS
     ponieważ
    1.16
     univerz
    1.05
     farba
    1.05
     gdyż
    1.02
    masker
    1.02
     vinagre
    1.02
    posiciones
    1.02
    ݯ
    1.01
    juin
    1.01
     diverting
    1.01
    Activations Density 0.125%

    No Known Activations