© 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. 22-GEMMASCOPE-RES-131K
    7. 26232
    Prev
    Next
    INDEX
    Explanations

    this. or self

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

    The neuron fires on object-member access (the “.” in expressions like self.x or this.y).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     női
    -1.09
    iglesia
    -1.09
    內容簡介
    -1.08
     második
    -1.06
     作り方
    -1.06
     měli
    -1.05
    breviations
    -1.03
     legjobb
    -1.02
     cintur
    -1.02
    lawayo
    -1.02
    POSITIVE LOGITS
     is
    0.98
    d
    0.88
    H
    0.86
    }=
    0.85
     type
    0.85
     =
    0.85
    6
    0.85
     c
    0.84
     компре
    0.83
    3
    0.82
    Activations Density 0.008%

    No Known Activations