© 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. 104314
    Prev
    Next
    INDEX
    Explanations

    taking it further, better, ahead, extension, variation

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

    The neuron fires on short phrases that describe going an extra “step” or bit beyond—e.g. “take it a step further,” “one step ahead,” or “a bit further.”

    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
     there
    -1.46
     localizar
    -1.23
     those
    -1.17
    compati
    -1.17
     acessar
    -1.16
    cisive
    -1.12
     in
    -1.11
    りと
    -1.09
     pouze
    -1.06
     leiden
    -1.05
    POSITIVE LOGITS
     but
    1.53
     question
    1.34
     Zeitpunkt
    1.30
    afterEach
    1.30
    phed
    1.27
    ২
    1.24
    odotus
    1.24
     übrigen
    1.23
     других
    1.21
     selben
    1.20
    Activations Density 0.066%

    No Known Activations