© 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. 68534
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

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

    This neuron never fires (all activations are zero), i.e. it does not 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
    ጧ
    -2.03
     تلك
    -1.91
    </b>
    -1.84
    もし
    -1.79
     assust
    -1.78
     RequestMethod
    -1.77
    }
    -1.73
     This
    -1.73
    目的是
    -1.71
    その
    -1.70
    POSITIVE LOGITS
    寕
    2.64
     hábit
    2.13
     successivo
    2.00
    很好的
    1.91
    大体
    1.89
     cittadino
    1.80
    tienen
    1.77
    っている
    1.77
     Sufficient
    1.74
    ほうが
    1.73
    Activations Density 0.004%

    No Known Activations