© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93278
    Prev
    Next
    INDEX
    Explanations

    self and own concepts

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

    The neuron detects words relating to self‐ownership or one’s own identity (e.g. “self,” “own,” “ownership,” “autologous,” etc.).

    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
    setCellStyle
    -1.03
    </u>
    -0.88
    àn
    -0.87
    mari
    -0.87
    </td>
    -0.86
     trái
    -0.85
    uintptr
    -0.85
     wspar
    -0.84
    饰演
    -0.84
    toHexString
    -0.83
    POSITIVE LOGITS
     self
    1.68
    self
    1.62
     own
    1.37
     SELF
    1.34
    自
    1.33
    Selbst
    1.25
    Self
    1.21
     OWN
    1.17
     vlastní
    1.16
    SELF
    1.16
    Activations Density 0.118%

    No Known Activations