© 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. 10-GEMMASCOPE-RES-131K
    7. 67497
    Prev
    Next
    INDEX
    Explanations

    specific start tokens

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

    This neuron activates on the meteorological abbreviation “Wx” (i.e. weather shorthand).

    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
     sguardo
    -1.07
    Assessing
    -0.96
     alimentazione
    -0.95
    onRequest
    -0.95
    ?),
    -0.94
    屺
    -0.94
    みが
    -0.94
     scheda
    -0.93
    írit
    -0.93
     könnt
    -0.93
    POSITIVE LOGITS
     with
    0.91
     ECR
    0.88
    ycznego
    0.85
    förmig
    0.84
    Nb
    0.83
    螃
    0.81
    惇
    0.81
     dynasties
    0.81
     nebo
    0.80
     Tsche
    0.80
    Activations Density 0.000%

    No Known Activations