© 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. 10-GEMMASCOPE-RES-131K
    7. 65172
    Prev
    Next
    INDEX
    Explanations

    dire and grave situations

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

    The neuron fires on occurrences of the character sequence “dire” (e.g. in dire, dire-wolf, dire-activity).

    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
    噫
    -2.30
    以上です
    -2.20
    푆
    -2.19
     рассказала
    -2.14
    ETIES
    -2.03
    棪
    -2.02
    薷
    -2.02
     suco
    -1.98
    礽
    -1.98
    chenta
    -1.97
    POSITIVE LOGITS
    7
    2.70
     
    2.30
    9
    2.28
     возможность
    2.22
    ly
    2.16
    1
    2.16
    ↵
    2.14
    6
    2.13
    ↵↵
    2.03
    4
    1.94
    Activations Density 0.005%

    No Known Activations