© 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. 34-GEMMASCOPE-RES-131K
    7. 73890
    Prev
    Next
    INDEX
    Explanations

    away and absent

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

    The neuron flags words and phrases that indicate someone is unavailable, absent, or incapacitated.

    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
     hecta
    -0.90
    えた
    -0.87
     Arnhem
    -0.82
    去吧
    -0.81
     pudieron
    -0.81
     existem
    -0.79
    を活用
    -0.79
    ñales
    -0.79
    styrelsen
    -0.78
     Unused
    -0.77
    POSITIVE LOGITS
     away
    3.52
     out
    2.56
    Away
    2.30
     Away
    2.25
    away
    2.16
     AWAY
    1.86
     abroad
    1.84
     absent
    1.80
    不在
    1.78
     gone
    1.70
    Activations Density 0.048%

    No Known Activations