© 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. 104573
    Prev
    Next
    INDEX
    Explanations

    Pages Label

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

    This neuron is effectively dead—it never fires and thus doesn’t detect any pattern.

    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
     all
    -1.67
    ̻
    -1.33
     from
    -1.33
     any
    -1.26
     in
    -1.26
     they
    -1.24
     januar
    -1.23
     after
    -1.21
    ervos
    -1.21
     get
    -1.20
    POSITIVE LOGITS
     horrifying
    1.26
     REALLY
    1.24
     somewhat
    1.24
     BECAUSE
    1.23
     essas
    1.22
     horrible
    1.21
    biendo
    1.20
     semelh
    1.20
    ,;
    1.19
    *;
    1.18
    Activations Density 0.000%

    No Known Activations