© 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. 67884
    Prev
    Next
    INDEX
    Explanations

    defunct entities

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

    The neuron flags occurrences of “defunct,” i.e. references to things that are discontinued or no longer in existence.

    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
    罴
    -2.89
    ꜆
    -2.84
    s
    -2.63
    ୩
    -2.53
    謦
    -2.52
    蚺
    -2.52
    नलोड
    -2.52
    ↵↵
    -2.45
    ୮
    -2.42
    ⭓
    -2.42
    POSITIVE LOGITS
    A
    2.72
    th
    2.52
     Hinblick
    2.42
    
    2.30
    禿
    2.30
    .
    2.23
    '
    2.23
     調整
    2.20
     your
    2.14
    皺
    2.13
    Activations Density 0.009%

    No Known Activations