© 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. 67063
    Prev
    Next
    INDEX
    Explanations

    targets

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

    The neuron fires specifically on occurrences of the token “targets.”

    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
    y
    -3.25
    o
    -3.19
    e
    -3.03
    s
    -3.00
    i
    -2.89
    u
    -2.83
    a
    -2.81
    胧
    -2.80
    ed
    -2.80
    ésil
    -2.78
    POSITIVE LOGITS
     
    3.83
        
    2.52
    本当に
    2.47
     позже
    2.42
    If
    2.41
    Initially
    2.36
    Ideally
    2.36
    筇
    2.34
    事も
    2.33
            
    2.27
    Activations Density 0.008%

    No Known Activations