© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38614
    Prev
    Next
    INDEX
    Explanations

    belief

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

    This neuron detects occurrences of words related to belief, especially forms of “believe” (e.g., believer, believing).

    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
    1
    -2.48
    翃
    -2.47
     longterm
    -2.14
    搽
    -2.11
    る
    -2.11
    ar
    -2.09
     \
    -2.08
    鉭
    -2.06
     linken
    -2.03
    
    -2.03
    POSITIVE LOGITS
    there
    2.52
    <i>
    2.36
     and
    2.28
     neto
    2.23
    翾
    2.20
     puerto
    2.13
    Ꮵ
    2.13
    </i>
    2.11
     prata
    2.11
    酲
    2.08
    Activations Density 0.001%

    No Known Activations