© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26292
    Prev
    Next
    INDEX
    Explanations

    holy phrases and terms

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

    The neuron activates on occurrences of the word “holy” (in any case) as used in religious or sacred contexts.

    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
    都不是
    -2.42
    b
    -2.30
     które
    -2.14
    ’
    -2.11
      
    -2.09
    ?
    -2.08
    .”
    -1.98
     [...]
    -1.96
     své
    -1.94
    ...
    -1.93
    POSITIVE LOGITS
    ]
    3.03
    }$
    2.89
    }
    2.55
    ኧ
    2.41
    】:
    2.36
     minori
    2.34
     Saltar
    2.34
    ⑉
    2.33
     espres
    2.31
     grail
    2.23
    Activations Density 0.005%

    No Known Activations