© 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. 9524
    Prev
    Next
    INDEX
    Explanations

    self-description and background

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

    The neuron is strongly activated by personal‐point‐of‐view tokens—i.e. first‐ and second‐person pronouns (I, you, we, etc.) and related conversational connectors.

    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
     reen
    -1.02
     xmm
    -0.90
    цов
    -0.90
    联
    -0.90
     geometries
    -0.87
    ľad
    -0.86
     temporaire
    -0.86
    żd
    -0.85
    忽
    -0.84
    styrelsen
    -0.84
    POSITIVE LOGITS
     profile
    1.64
     information
    1.49
     biography
    1.44
     Profile
    1.44
    ynchronously
    1.41
     biographical
    1.41
    Profile
    1.38
     personality
    1.30
     about
    1.29
     autobiography
    1.23
    Activations Density 0.050%

    No Known Activations