© 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. 34-GEMMASCOPE-RES-131K
    7. 107856
    Prev
    Next
    INDEX
    Explanations

    positive sentiment smiley :)

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

    This neuron flags unusually rare or low‐frequency subword tokens.

    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
     at
    -1.26
     in
    -1.25
     by
    -1.23
     makes
    -1.11
                        
    -1.10
     with
    -1.09
     before
    -1.07
     goes
    -1.05
     does
    -1.05
     on
    -1.05
    POSITIVE LOGITS
     expliquer
    1.09
     bén
    1.02
     ouver
    1.02
     personnal
    0.99
     wail
    0.98
     économ
    0.98
     renfor
    0.97
    ሺ
    0.97
     publicités
    0.94
     interrom
    0.94
    Activations Density 0.012%

    No Known Activations