© 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. 67645
    Prev
    Next
    INDEX
    Explanations

    other parts of

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

    The neuron activates on occurrences of the phrase “other parts.”

    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
     now
    -1.63
    ꒦
    -1.60
     dichas
    -1.55
     nowadays
    -1.55
     themselves
    -1.45
     every
    -1.43
    見えて
    -1.41
     each
    -1.39
     Geben
    -1.39
    のは
    -1.35
    POSITIVE LOGITS
    worldly
    2.06
                
    1.78
    та
    1.61
     []:
    1.60
    BindingResult
    1.57
    _->
    1.53
    )>>
    1.53
     \%}$
    1.52
    getMenuInflater
    1.51
     ,‬
    1.51
    Activations Density 0.025%

    No Known Activations