© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48916
    Prev
    Next
    INDEX
    Explanations

    whether or not

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

    The neuron fires strongly on whatever token occurs at the very end of a text segment, i.e. the final word before the closing boundary.

    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
     esportivo
    -1.36
     traseiro
    -1.32
    /−
    -1.13
    蛭
    -1.13
    thè
    -1.10
    🕞
    -1.09
     isolada
    -1.09
     explicou
    -1.08
     mathvariant
    -1.07
    jska
    -1.06
    POSITIVE LOGITS
     not
    9.50
    not
    4.47
    Not
    3.92
     не
    3.91
     Not
    3.72
     NOT
    3.50
    ไม่
    3.28
     नहीं
    3.14
     không
    3.11
     nicht
    3.08
    Activations Density 0.049%

    No Known Activations