© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75625
    Prev
    Next
    INDEX
    Explanations

    anecdotal evidence or reports

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

    The neuron fires on occurrences of “anecdotal” (and its variants), flagging mentions of anecdotal evidence or personal‐experience claims.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     todav
    -0.94
    ")]
    
    -0.90
     godk
    -0.87
     pastillas
    -0.86
     mme
    -0.85
     THURSDAY
    -0.85
    стю
    -0.85
    _$
    -0.84
    ;*/
    -0.84
     tost
    -0.84
    POSITIVE LOGITS
     anecdotal
    5.00
    Ane
    4.31
     ane
    4.25
     Ane
    4.03
     anecdotes
    3.69
     anecdote
    3.34
     ане
    2.59
     anecd
    2.38
    ecd
    1.80
     observations
    1.75
    Activations Density 0.077%

    No Known Activations