© 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. 34-GEMMASCOPE-RES-131K
    7. 57289
    Prev
    Next
    INDEX
    Explanations

    long-term outcomes and planning

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

    This neuron detects occurrences of the phrase “long term” (especially in “long-term”) in the text.

    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
    İstin
    -1.12
    昺
    -1.10
    NEYS
    -1.05
    schwar
    -1.03
    reloj
    -1.03
     indietro
    -1.02
    kleine
    -1.02
     коротки
    -1.00
    Daha
    -1.00
     brief
    -0.98
    POSITIVE LOGITS
     (>
    1.34
     planning
    1.23
     goals
    1.20
     vision
    1.16
     viability
    1.11
     ago
    1.06
     strategy
    1.05
     memory
    1.05
     perspective
    1.03
     goal
    1.02
    Activations Density 0.045%

    No Known Activations