© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 28928
    Prev
    Next
    INDEX
    Explanations

    goal achievement

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

    This neuron detects action verbs that describe designing, developing, managing, or otherwise optimizing and improving something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    cended
    -1.26
    ()};
    -1.16
    actic
    -1.16
    esor
    -1.13
    tifications
    -1.13
    opportunity
    -1.13
    ℉
    -1.12
    mbi
    -1.11
    brough
    -1.11
    haviours
    -1.09
    POSITIVE LOGITS
     more
    1.45
     those
    1.39
     better
    1.34
     about
    1.30
     often
    1.30
     their
    1.26
     both
    1.24
     also
    1.23
     know
    1.23
     easier
    1.20
    Activations Density 0.184%

    No Known Activations